Gemini tinkering 3

* Add helpers for creating RenderPipelineParams for backend tests

BUGS=[398199600]

* Move all backend tests over to use cyan as the clear color

.github/actions/dep-versions/action.yml

@@ -3,5 +3,5 @@ runs:
   using: "composite"
   steps:
     - name: Set up dependency versions
-      shell: bash    
+      shell: bash
       run: cat ./build/common/versions >> $GITHUB_ENV

.github/actions/web-prereq/action.yml

@@ -0,0 +1,16 @@
+name: 'Web Preqrequisites'
+runs:
+  using: "composite"
+  steps:
+    - uses: ./.github/actions/dep-versions
+    - name: Cache EMSDK
+      id: emsdk-cache
+      uses: actions/cache@v4 # Use a specific version
+      with:
+        path: emsdk
+        key: ${{ runner.os }}-emsdk-${{ env.GITHUB_EMSDK_VERSION }}
+    - name: Install Web Prerequisites
+      shell: bash
+      run: |
+        bash ./build/common/get-emscripten.sh
+        echo "EMSDK=$PWD/emsdk" >> $GITHUB_ENV

.github/workflows/mac-continuous.yml

@@ -26,4 +26,4 @@ jobs:
           path: out/filament-release-darwin.tgz
       - name: Check public headers
         run: |
-          build/common/check-headers.sh out/release/filament/include
+          test/check-headers/test.sh out/release/filament/include

.github/workflows/presubmit.yml

@@ -96,6 +96,7 @@ jobs:
         with:
           fetch-depth: 0
       - uses: ./.github/actions/linux-prereq
+      - uses: ./.github/actions/web-prereq
       - name: Run build script
         run: |
           cd build/web && printf "y" | ./build.sh presubmit
@@ -123,13 +124,15 @@ jobs:
       - uses: ./.github/actions/mac-prereq
       - name: Cache Mesa and deps
         id: mesa-cache
-        uses: actions/cache@v4 # Use a specific version
+        uses: actions/cache@v4
         with:
           path: mesa
           key: ${{ runner.os }}-mesa-deps-2-${{ vars.MESA_VERSION }}
-      - name: Get Mesa
+      - name: Prerequisites
-        id: mesa-prereq
+        id: prereqs
-        run: bash test/utils/get_mesa.sh
+        run: |
+          bash build/common/get-mesa.sh
+          pip install tifffile numpy
       - name: Run Test
         run: bash test/renderdiff/test.sh
       - uses: actions/upload-artifact@v4
@@ -150,8 +153,8 @@ jobs:
       - name: Run test
         run: ./out/cmake-debug/libs/filamat/test_filamat --gtest_filter=MaterialCompiler.Wgsl*
 
-  code-correcteness:
+  test-code-correctness:
-    name: code-correctness
+    name: test-code-correctness
     runs-on: 'macos-14-xlarge'
     steps:
       - uses: actions/checkout@v4.1.6

.github/workflows/release.yml

@@ -65,13 +65,9 @@ jobs:
 
   build-mac:
     name: build-mac
-    runs-on: ${{ matrix.os }}
+    runs-on: macos-14-xlarge
     if: github.event_name == 'release' || github.event.inputs.platform == 'desktop'
 
-    strategy:
-      matrix:
-        os: [macos-14-xlarge, ubuntu-22.04-32core]
-
     steps:
       - name: Decide Git ref
         id: git_ref
@@ -118,6 +114,7 @@ jobs:
         with:
           ref: ${{ steps.git_ref.outputs.ref }}
       - uses: ./.github/actions/linux-prereq
+      - uses: ./.github/actions/web-prereq
       - name: Run build script
         env:
           TAG: ${{ steps.git_ref.outputs.tag }}
@@ -166,6 +163,9 @@ jobs:
           mv out/filamat-android-release.aar out/filamat-${TAG}-android.aar
           mv out/gltfio-android-release.aar out/gltfio-${TAG}-android.aar
           mv out/filament-utils-android-release.aar out/filament-utils-${TAG}-android.aar
+          cd out/android-release/filament
+          tar -czf ../../filament-${TAG}-android-native.tgz .
+          cd ../../..
       - name: Sign sample-gltf-viewer
         run: |
           echo "${APK_KEYSTORE_BASE64}" > filament.jks.base64
@@ -187,7 +187,7 @@ jobs:
           script: |
             const upload = require('./build/common/upload-release-assets');
             const { TAG } = process.env;
-            const globber = await glob.create(['out/*.aar', 'out/*.apk'].join('\n'));
+            const globber = await glob.create(['out/*.aar', 'out/*.apk', 'out/*.tgz'].join('\n'));
             await upload({ github, context }, await globber.glob(), TAG);
 
   build-ios:

.github/workflows/web-continuous.yml

@@ -17,6 +17,7 @@ jobs:
         with:
           fetch-depth: 0
       - uses: ./.github/actions/linux-prereq
+      - uses: ./.github/actions/web-prereq
       - name: Run build script
         run: |
           cd build/web && printf "y" | ./build.sh continuous

BUILDING.md

@@ -363,6 +363,8 @@ python ./emsdk.py activate latest
 source ./emsdk_env.sh
 ```
 
+Alternatively, you can try running the script `build/common/get-emscripten.sh`.
+
 After this you can invoke the [easy build](#easy-build) script as follows:
 
 ```shell

README.md

@@ -31,7 +31,7 @@ repositories {
 }
 
 dependencies {
-    implementation 'com.google.android.filament:filament-android:1.59.4'
+    implementation 'com.google.android.filament:filament-android:1.60.1'
 }
 ```
 
@@ -51,7 +51,7 @@ Here are all the libraries available in the group `com.google.android.filament`:
 iOS projects can use CocoaPods to install the latest release:
 
 ```shell
-pod 'Filament', '~> 1.59.4'
+pod 'Filament', '~> 1.60.1'
 ```
 
 ## Documentation

RELEASE_NOTES.md

@@ -7,6 +7,22 @@ A new header is inserted each time a *tag* is created.
 Instead, if you are authoring a PR for the main branch, add your release note to
 [NEW_RELEASE_NOTES.md](./NEW_RELEASE_NOTES.md).
 
+## v1.61.0
+
+- materials: sampler now export their type in the material binary [⚠️ **New Material Version**]
+- samples/texturedquad.cpp now has CLI to select backend api
+- samples/hellopbr.cpp CLI now allows for selecting webgpu
+
+## v1.60.1
+
+
+## v1.60.0
+
+- materials: remove dependence on per-view descset layout from filamat. [⚠️ **New Material Version**]
+- matc non-functional change: Update GLSL postprocessor to
+  isolate calls to SPVRemap from calls to SPIRV-Cross.
+
+
 ## v1.59.5
 
 

android/filament-android/src/main/java/com/google/android/filament/View.java

@@ -1801,6 +1801,22 @@ public class View {
      * @see setAmbientOcclusionOptions()
      */
     public static class AmbientOcclusionOptions {
+        public enum AmbientOcclusionType {
+            /**
+             * use Scalable Ambient Occlusion
+             */
+            SAO,
+            /**
+             * use Ground Truth-Based Ambient Occlusion
+             */
+            GTAO,
+        }
+
+        /**
+         * Type of ambient occlusion algorithm.
+         */
+        @NonNull
+        public AmbientOcclusionOptions.AmbientOcclusionType aoType = AmbientOcclusionOptions.AmbientOcclusionType.SAO;
         /**
          * Ambient Occlusion radius in meters, between 0 and ~10.
          */
@@ -1810,7 +1826,8 @@ public class View {
          */
         public float power = 1.0f;
         /**
-         * Self-occlusion bias in meters. Use to avoid self-occlusion. Between 0 and a few mm.
+         * Self-occlusion bias in meters. Use to avoid self-occlusion.
+         * Between 0 and a few mm. No effect when aoType set to GTAO
          */
         public float bias = 0.0005f;
         /**
@@ -1826,12 +1843,12 @@ public class View {
          */
         public float bilateralThreshold = 0.05f;
         /**
-         * affects # of samples used for AO.
+         * affects # of samples used for AO and params for filtering
          */
         @NonNull
         public QualityLevel quality = QualityLevel.LOW;
         /**
-         * affects AO smoothness
+         * affects AO smoothness. Recommend setting to HIGH when aoType set to GTAO.
          */
         @NonNull
         public QualityLevel lowPassFilter = QualityLevel.MEDIUM;
@@ -1849,7 +1866,7 @@ public class View {
          */
         public boolean bentNormals = false;
         /**
-         * min angle in radian to consider
+         * min angle in radian to consider. No effect when aoType set to GTAO.
          */
         public float minHorizonAngleRad = 0.0f;
         /**
@@ -1904,6 +1921,19 @@ public class View {
          */
         public boolean ssctEnabled = false;
 
+        /**
+         * Ground Truth-base Ambient Occlusion (GTAO) options
+         */
+        public int gtaoSampleSliceCount = 4;
+        /**
+         * Ground Truth-base Ambient Occlusion (GTAO) options
+         */
+        public int gtaoSampleStepsPerSlice = 3;
+        /**
+         * Ground Truth-base Ambient Occlusion (GTAO) options
+         */
+        public float gtaoThicknessHeuristic = 0.004f;
+
     }
 
     /**

android/gradle.properties

@@ -1,5 +1,5 @@
 GROUP=com.google.android.filament
-VERSION_NAME=1.59.4
+VERSION_NAME=1.60.1
 
 POM_DESCRIPTION=Real-time physically based rendering engine for Android.
 

build.sh

@@ -151,7 +151,7 @@ function print_fgviewer_help {
 }
 
 # Unless explicitly specified, NDK version will be selected as highest available version within same major release chain
-FILAMENT_NDK_VERSION=${FILAMENT_NDK_VERSION:-$(cat `dirname $0`/build/android/ndk.version | cut -f 1 -d ".")}
+FILAMENT_NDK_VERSION=${FILAMENT_NDK_VERSION:-$(cat `dirname $0`/build/common/versions | grep GITHUB_NDK_VERSION | sed s/GITHUB_NDK_VERSION=//g | cut -f 1 -d ".")}
 
 # Requirements
 CMAKE_MAJOR=3
@@ -463,16 +463,6 @@ function ensure_android_build {
         echo "Error: Android NDK side-by-side version ${FILAMENT_NDK_VERSION} or compatible must be installed, exiting"
         exit 1
     fi
-
-    local cmake_version=$(cmake --version)
-    if [[ "${cmake_version}" =~ ([0-9]+)\.([0-9]+)\.[0-9]+ ]]; then
-        if [[ "${BASH_REMATCH[1]}" -lt "${CMAKE_MAJOR}" ]] || \
-           [[ "${BASH_REMATCH[2]}" -lt "${CMAKE_MINOR}" ]]; then
-            echo "Error: cmake version ${CMAKE_MAJOR}.${CMAKE_MINOR}+ is required," \
-                 "${BASH_REMATCH[1]}.${BASH_REMATCH[2]} installed, exiting"
-            exit 1
-        fi
-    fi
 }
 
 function build_android {

build/android/build.sh

@@ -1,28 +1,6 @@
 #!/bin/bash
 
-# Usage: the first argument selects the build type:
+source `dirname $0`/../common/ci-check.sh
-# - release, to build release only
-# - debug, to build debug only
-# - continuous, to build release and debug
-# - presubmit, for presubmit builds
-#
-# The default is release
-
-echo "This script is intended to run in a CI environment and may modify your current environment."
-echo "Please refer to BUILDING.md for more information."
-
-read -r -p "Do you wish to proceed (y/n)? " choice
-case "${choice}" in
-    y|Y)
-              echo "Build will proceed..."
-              ;;
-    n|N)
-          exit 0
-          ;;
-          *)
-        exit 0
-        ;;
-esac
 
 set -e
 set -x
@@ -30,11 +8,6 @@ set -x
 UNAME=`echo $(uname)`
 LC_UNAME=`echo $UNAME | tr '[:upper:]' '[:lower:]'`
 
-# build-common.sh will generate the following variables:
-#     $GENERATE_ARCHIVES
-#     $BUILD_DEBUG
-#     $BUILD_RELEASE
-source `dirname $0`/../common/ci-common.sh
 source `dirname $0`/../common/build-common.sh
 
 if [[ "$GITHUB_WORKFLOW" ]]; then

build/common/build-common.sh

@@ -1,5 +1,20 @@
 #!/bin/bash
 
+# build-common.sh will generate the following variables:
+#     $GENERATE_ARCHIVES
+#     $BUILD_DEBUG
+#     $BUILD_RELEASE
+
+# Typically a build script (build.sh) would source this script. For example,
+#   source `dirname $0`/../common/build-common.sh
+
+# Usage: the first argument selects the build type:
+# - release, to build release only
+# - debug, to build debug only
+# - continuous, to build release and debug
+# - presubmit, for presubmit builds
+#
+# The default is release
 if [[ ! "$TARGET" ]]; then
     if [[ "$1" ]]; then
         TARGET=$1

build/common/ci-check.sh

@@ -0,0 +1,19 @@
+echo "This script is intended to run in a CI environment and may modify your current environment."
+echo "Please refer to BUILDING.md for more information."
+
+read -r -p "Do you wish to proceed (y/n)? " choice
+case "${choice}" in
+    y|Y)
+	      echo "Build will proceed..."
+	      ;;
+    n|N)
+    	  exit 0
+    	  ;;
+	  *)
+        exit 0
+        ;;
+esac
+
+if [[ "$GITHUB_WORKFLOW" ]]; then
+    echo "Running workflow $GITHUB_WORKFLOW (event: $GITHUB_EVENT_NAME, action: $GITHUB_ACTION)"
+fi

build/common/ci-common.sh

@@ -1,5 +0,0 @@
-#!/bin/bash
-
-if [[ "$GITHUB_WORKFLOW" ]]; then
-    echo "Running workflow $GITHUB_WORKFLOW (event: $GITHUB_EVENT_NAME, action: $GITHUB_ACTION)"
-fi

build/common/get-emscripten.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+
+if [ -d "./emsdk" ]; then
+    echo "emsdk folder found. Assume emsdk has been installed."
+    cd emsdk
+    ./emsdk activate latest
+    source ./emsdk_env.sh
+    export EMSDK="$PWD"
+    cd ..
+    exit 0
+fi
+
+# Install emscripten.
+EMSDK_VERSION=${GITHUB_EMSDK_VERSION-3.1.60}
+curl -L https://github.com/emscripten-core/emsdk/archive/refs/tags/${EMSDK_VERSION}.zip > emsdk.zip
+unzip emsdk.zip ; mv emsdk-* emsdk ; cd emsdk
+./emsdk install latest
+./emsdk activate latest
+source ./emsdk_env.sh
+
+export EMSDK="$PWD"
+cd ..

build/common/get-mesa.sh

@@ -14,9 +14,9 @@
 
 #!/usr/bin/bash
 
-set -x
+set -e
 if [[ "$GITHUB_WORKFLOW" ]]; then
-    set -e
+    set -x
 fi
 
 OS_NAME=$(uname -s)
@@ -35,7 +35,7 @@ source ${ORIG_DIR}/venv/bin/activate
 
 NEEDED_PYTHON_DEPS=("mako" "setuptools" "pyyaml")
 for cmd in "${NEEDED_PYTHON_DEPS[@]}"; do
-    if ! python3 -m pip show "${cmd}" >/dev/null 2>&1; then
+    if ! python3 -m pip show -q "${cmd}" >/dev/null 2>&1; then
         python3 -m pip install ${cmd}
     fi
 done
@@ -145,6 +145,6 @@ deactivate
 popd
 
 if [[ "$GITHUB_WORKFLOW" ]]; then
-    set +e
+    set +x
 fi
-set +x
+set +e

build/common/versions

@@ -3,4 +3,5 @@ GITHUB_CMAKE_VERSION=3.19.5
 GITHUB_NINJA_VERSION=1.10.2
 GITHUB_MESA_VERSION=24.2.1
 GITHUB_LLVM_VERSION=16
-GITHUB_NDK_VERSION=27.0.11718014
+GITHUB_NDK_VERSION=27.0.11718014
+GITHUB_EMSDK_VERSION=3.1.60

build/ios/build.sh

@@ -1,35 +1,11 @@
 #!/bin/bash
 
-# Usage: the first argument selects the build type:
+source `dirname $0`/../common/ci-check.sh
-# - release, to build release only
-# - debug, to build debug only
-# - continuous, to build release and debug
-# - presubmit, for presubmit builds
-#
-# The default is release
-
-echo "This script is intended to run in a CI environment and may modify your current environment."
-echo "Please refer to BUILDING.md for more information."
-
-read -r -p "Do you wish to proceed (y/n)? " choice
-case "${choice}" in
-    y|Y)
-	      echo "Build will proceed..."
-	      ;;
-    n|N)
-    	  exit 0
-    	  ;;
-	  *)
-        exit 0
-        ;;
-esac
 
 set -e
 set -x
 
-source `dirname $0`/../common/ci-common.sh
 source `dirname $0`/../common/build-common.sh
-
 pushd `dirname $0`/../.. > /dev/null
 
 # If we're generating an archive for release or continuous builds, then we'll also build for the

build/linux/build.sh

@@ -1,38 +1,11 @@
 #!/bin/bash
 
-# Usage: the first argument selects the build type:
+source `dirname $0`/../common/ci-check.sh
-# - release, to build release only
-# - debug, to build debug only
-# - continuous, to build release and debug
-# - presubmit, for presubmit builds
-#
-# The default is release
-
-echo "This script is intended to run in a CI environment and may modify your current environment."
-echo "Please refer to BUILDING.md for more information."
-
-read -r -p "Do you wish to proceed (y/n)? " choice
-case "${choice}" in
-    y|Y)
-	      echo "Build will proceed..."
-	      ;;
-    n|N)
-    	  exit 0
-    	  ;;
-	  *)
-        exit 0
-        ;;
-esac
 
 set -e
 set -x
 
-# build-common.sh will generate the following variables:
-#     $GENERATE_ARCHIVES
-#     $BUILD_DEBUG
-#     $BUILD_RELEASE
-source `dirname $0`/../common/ci-common.sh
 source `dirname $0`/../common/build-common.sh
-
 pushd `dirname $0`/../.. > /dev/null
+
 ./build.sh -c $RUN_TESTS $GENERATE_ARCHIVES $BUILD_DEBUG $BUILD_RELEASE

build/mac/build.sh

@@ -1,34 +1,11 @@
 #!/bin/bash
 
-# Usage: the first argument selects the build type:
+source `dirname $0`/../common/ci-check.sh
-# - release, to build release only
-# - debug, to build debug only
-# - continuous, to build release and debug
-# - presubmit, for presubmit builds
-#
-# The default is release
-
-echo "This script is intended to run in a CI environment and may modify your current environment."
-echo "Please refer to BUILDING.md for more information."
-
-read -r -p "Do you wish to proceed (y/n)? " choice
-case "${choice}" in
-    y|Y)
-	      echo "Build will proceed..."
-	      ;;
-    n|N)
-    	  exit 0
-    	  ;;
-	  *)
-        exit 0
-        ;;
-esac
 
 set -e
 set -x
 
-source `dirname $0`/../common/ci-common.sh
 source `dirname $0`/../common/build-common.sh
-
 pushd `dirname $0`/../.. > /dev/null
+
 ./build.sh -c $RUN_TESTS $GENERATE_ARCHIVES $BUILD_DEBUG $BUILD_RELEASE

build/web/build.sh

@@ -1,34 +1,10 @@
 #!/bin/bash
 
-# Usage: the first argument selects the build type:
+source `dirname $0`/../common/ci-check.sh
-# - release, to build release only
-# - debug, to build debug only
-# - continuous, to build release and debug
-# - presubmit, for presubmit builds
-#
-# The default is release
-
-echo "This script is intended to run in a CI environment and may modify your current environment."
-echo "Please refer to BUILDING.md for more information."
-
-read -r -p "Do you wish to proceed (y/n)? " choice
-case "${choice}" in
-    y|Y)
-	      echo "Build will proceed..."
-	      ;;
-    n|N)
-    	  exit 0
-    	  ;;
-	  *)
-        exit 0
-        ;;
-esac
 
 set -e
 set -x
 
-source `dirname $0`/../common/ci-common.sh
-source `dirname $0`/ci-common.sh
 source `dirname $0`/../common/build-common.sh
 pushd `dirname $0`/../.. > /dev/null
 

build/web/ci-common.sh

@@ -1,11 +0,0 @@
-#!/bin/bash
-
-# Install emscripten.
-curl -L https://github.com/emscripten-core/emsdk/archive/refs/tags/3.1.60.zip > emsdk.zip
-unzip emsdk.zip ; mv emsdk-* emsdk ; cd emsdk
-./emsdk install latest
-./emsdk activate latest
-source ./emsdk_env.sh
-
-export EMSDK="$PWD"
-cd ..

docs_src/markdeep/Materials.md.html

@@ -1023,8 +1023,12 @@ samplerCubemap         | Cubemap texture
 [Table [materialParamsTypes]: Material parameter types]
 
 Samplers
-:     Sampler types can also specify a `format` which can be either `int` or `float` (defaults to
+:     Sampler types can specify additional options:
-      `float`).
+
+      - `format`: either `int` or `float` (defaults to `float`).
+      - `stages`: array of strings containing the list of shader stages this
+        sampler can be accessed from. Each entry must be either `vertex` or
+        `fragment` (defaults to both).
 
 Arrays
 :     A parameter can define an array of values by appending `[size]` after the type name, where

docs_src/src/SUMMARY.md

@@ -18,6 +18,8 @@
     - [Metal](./notes/metal_debugging.md)
     - [Vulkan](./notes/vulkan_debugging.md)
     - [SPIR-V](./notes/spirv_debugging.md)
+    - [Running with ASAN and UBSAN](./notes/asan_ubsan.md)
+    - [Using Instruments on macOS](./notes/instruments.md)
   - [Libraries](./notes/libs.md)
     - [bluegl](./dup/bluegl.md)
     - [bluevk](./dup/bluevk.md)

docs_src/src/notes/asan_ubsan.md

@@ -0,0 +1,41 @@
+# Running with ASAN/UBSAN
+
+## Enabling
+
+When building though build.sh, pass the `-b` flag. This sets the cmake variable
+`FILAMENT_ENABLE_ASAN_UBSAN=ON` which eventually passes `"-fsanitize=address -fsanitize=undefined"`
+to all compile and link operations.
+
+If building through CMake directly, or an IDE like CLion that doesn't use build.sh, instead pass
+`-DFILAMENT_ENABLE_ASAN_UBSAN=ON` to cmake in order to get the same result.
+
+## Getting memory leak detection on Mac
+
+Memory leak detection isn't enabled by default on MacOS. There are two issues to address, first is
+using a version of clang that supports memory leak detection and second is enabling it at runtime.
+
+The version of clang distributed by Apple (with a version like "Apple clang version 16.0.0") doesn't
+currently support leak detection at all. Instead you will need to get or build a different LLVM,
+such as the one distributed through homebrew and get CMake to use that instead.
+
+Then during runtime you'll need to have the environment variable `ASAN_OPTIONS` include the option
+`detect_leaks=1`. Multiple `ASAN_OPTIONS` values are concatenated with `:`.
+
+## Getting memory leak output in CLion
+
+### Setting variables
+
+Under `Settings | Build, Execution, Deployment | Dynamic Analysis Tools | Sanitizers` there is an
+ASAN Settings field that overrides whatever other `ASAN_OPTIONS` you might set elsewhere, so you
+must use that instead of setting it through your Run/Debug Configuration.
+
+To pass `-DFILAMENT_ENABLE_ASAN_UBSAN=ON` to CMake you'll want to create a new CMake Profile and
+pass it as a CMake argument.
+
+### Avoiding losing output
+
+CMake will consume ASAN output and display it through a separate "Sanitizers" tab. Unfortunately
+certain leak detection errors that interrupt the executable seem to not show up in this tab, but are
+still removed from the user-visible console output. If this is happening and you need to see the
+unfiltered console output you'll need to go to `Settings | Build, Execution, Deployment | Dynamic
+Analysis Tools | Sanitizers` and uncheck "Use visual representation for Sanitizer's output".

docs_src/src/notes/instruments.md

@@ -0,0 +1,36 @@
+# Using Instruments on macOS
+
+When running a binary under Instruments on macOS, you may run into the following issue when
+launching or attaching to an executable:
+
+```
+Failed to gain authorization
+Recovery Suggestion: Target binary needs to be debuggable and signed with 'get-task-allow'
+```
+
+This is a security precaution; the solution is to code sign the binary with the
+`com.apple.security.get-task-allow` entitlement.
+
+1. Create an `entitlements.plist` file with the following contents:
+
+```
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+    <key>com.apple.security.get-task-allow</key>
+    <true/>
+</dict>
+</plist>
+```
+
+2. Run the following command:
+
+```
+codesign -s - --entitlements entitlements.plist <binary>
+```
+
+Replace `<binary>` with the name of the binary, for example: `out/cmake-debug/samples/gltf_viewer`.
+
+Afterwards, you should be able to successfully launch and attach to the executable using
+Instruments.

filament/CMakeLists.txt

@@ -262,6 +262,8 @@ set(MATERIAL_SRCS
         src/materials/ssao/mipmapDepth.mat
         src/materials/ssao/sao.mat
         src/materials/ssao/saoBentNormals.mat
+        src/materials/ssao/gtao.mat
+        src/materials/ssao/gtaoBentNormals.mat
         src/materials/vsmMipmap.mat
 )
 
@@ -318,8 +320,6 @@ endif()
 # Definitions
 # ==================================================================================================
 
-# "2" corresponds to SYSTRACE_TAG_FILEMENT (See: utils/Systrace.h)
-add_definitions(-DSYSTRACE_TAG=2)
 add_definitions(-DFILAMENT_DFG_LUT_SIZE=${DFG_LUT_SIZE})
 add_definitions(
     -DFILAMENT_PER_RENDER_PASS_ARENA_SIZE_IN_MB=${FILAMENT_PER_RENDER_PASS_ARENA_SIZE_IN_MB}
@@ -463,6 +463,28 @@ add_custom_command(
         APPEND
 )
 
+add_custom_command(
+        OUTPUT "${MATERIAL_DIR}/gtao.filamat"
+        DEPENDS src/materials/ssao/ssaoUtils.fs
+        DEPENDS src/materials/ssao/ssct.fs
+        DEPENDS src/materials/utils/depthUtils.fs
+        DEPENDS src/materials/utils/geometry.fs
+        DEPENDS src/materials/ssao/gtaoImpl.fs
+        DEPENDS src/materials/ssao/ssctImpl.fs
+        APPEND
+)
+
+add_custom_command(
+        OUTPUT "${MATERIAL_DIR}/gtaoBentNormals.filamat"
+        DEPENDS src/materials/ssao/ssaoUtils.fs
+        DEPENDS src/materials/ssao/ssct.fs
+        DEPENDS src/materials/utils/depthUtils.fs
+        DEPENDS src/materials/utils/geometry.fs
+        DEPENDS src/materials/ssao/gtaoImpl.fs
+        DEPENDS src/materials/ssao/ssctImpl.fs
+        APPEND
+)
+
 add_custom_command(
         OUTPUT "${MATERIAL_DIR}/bilateralBlur.filamat"
         DEPENDS src/materials/ssao/ssaoUtils.fs

filament/backend/CMakeLists.txt

@@ -5,18 +5,6 @@ set(TARGET backend)
 set(PUBLIC_HDR_DIR include)
 set(GENERATION_ROOT ${CMAKE_CURRENT_BINARY_DIR})
 
-# ==================================================================================================
-# Compilation options
-# ==================================================================================================
-#
-set(BACKEND_SANITIZATION "" CACHE STRING "Sanitization option")
-set_property(CACHE BACKEND_SANITIZATION PROPERTY STRINGS ";ASAN")
-
-set(BACKEND_SANITIZERS)
-if (BACKEND_SANITIZATION STREQUAL "ASAN")
-    set(BACKEND_SANITIZERS -fsanitize=address)
-endif()
-
 # ==================================================================================================
 # Sources and headers
 # ==================================================================================================
@@ -302,12 +290,6 @@ if (ANDROID)
     list(APPEND SRCS src/BackendUtilsAndroid.cpp)
 endif()
 
-# ==================================================================================================
-# Definitions
-# ==================================================================================================
-# "2" corresponds to SYSTRACE_TAG_FILEMENT (See: utils/Systrace.h)
-add_definitions(-DSYSTRACE_TAG=2 )
-
 # ==================================================================================================
 # Includes & target definition
 # ==================================================================================================
@@ -484,7 +466,6 @@ target_compile_options(${TARGET} PRIVATE
         ${OSMESA_COMPILE_FLAGS}
         $<$<CONFIG:Release>:${OPTIMIZATION_FLAGS}>
         $<$<AND:$<PLATFORM_ID:Darwin>,$<CONFIG:Release>>:${DARWIN_OPTIMIZATION_FLAGS}>
-        ${BACKEND_SANITIZERS}
 )
 
 if (FILAMENT_SUPPORTS_METAL)
@@ -495,8 +476,6 @@ if (FILAMENT_SUPPORTS_WEBGPU)
     target_compile_definitions(${TARGET} PRIVATE $<$<BOOL:${FILAMENT_WEBGPU_IMMEDIATE_ERROR_HANDLING}>:FILAMENT_WEBGPU_IMMEDIATE_ERROR_HANDLING>)
 endif()
 
-target_link_options(${TARGET} PRIVATE ${BACKEND_SANITIZERS})
-
 target_link_libraries(${TARGET} PRIVATE
         ${OSMESA_LINKER_FLAGS}
         $<$<AND:$<PLATFORM_ID:Linux>,$<CONFIG:Release>>:${LINUX_LINKER_OPTIMIZATION_FLAGS}>
@@ -566,8 +545,6 @@ if (APPLE AND NOT IOS)
          test/test_RenderExternalImage.cpp)
     add_library(backend_test STATIC ${BACKEND_TEST_SRC})
     target_link_libraries(backend_test PUBLIC ${BACKEND_TEST_LIBS})
-    target_compile_options(backend_test PRIVATE ${BACKEND_SANITIZERS})
-    target_link_options(backend_test PRIVATE ${BACKEND_SANITIZERS})
 
     set(BACKEND_TEST_DEPS
             OSDependent
@@ -606,7 +583,6 @@ if (APPLE AND NOT IOS)
        # linker from removing "unused" symbols.
        target_link_libraries(backend_test_mac PRIVATE -force_load backend_test)
        set_target_properties(backend_test_mac PROPERTIES FOLDER Tests)
-       target_link_options(backend_test_mac PRIVATE ${BACKEND_SANITIZERS})
 
        # This is needed after XCode 15.3
        set_target_properties(backend_test_mac PROPERTIES BUILD_WITH_INSTALL_RPATH TRUE)
@@ -616,8 +592,6 @@ endif()
 
 if (LINUX)
     add_executable(backend_test_linux test/linux_runner.cpp ${BACKEND_TEST_SRC})
-    target_compile_options(backend_test_linux PRIVATE ${BACKEND_SANITIZERS})
-    target_link_options(backend_test_linux PRIVATE ${BACKEND_SANITIZERS})
     target_link_libraries(backend_test_linux PRIVATE ${BACKEND_TEST_LIBS})
     set_target_properties(backend_test_linux PROPERTIES FOLDER Tests)
 endif()

filament/backend/include/backend/BufferDescriptor.h

@@ -20,10 +20,15 @@
 #define TNT_FILAMENT_BACKEND_BUFFERDESCRIPTOR_H
 
 #include <utils/compiler.h>
-#include <utils/ostream.h>
+
+#include <utility>
 
 #include <stddef.h>
 
+namespace utils::io {
+class ostream;
+} // namespace utils::io
+
 namespace filament::backend {
 
 class CallbackHandler;
@@ -89,8 +94,8 @@ public:
      * @param callback  A callback used to release the CPU buffer from this BufferDescriptor
      * @param user      An opaque user pointer passed to the callback function when it's called
      */
-    BufferDescriptor(void const* buffer, size_t size,
+    BufferDescriptor(void const* buffer, size_t const size,
-            Callback callback = nullptr, void* user = nullptr) noexcept
+            Callback const callback = nullptr, void* user = nullptr) noexcept
                 : buffer(const_cast<void*>(buffer)), size(size), mCallback(callback), mUser(user) {
     }
 
@@ -98,11 +103,12 @@ public:
      * Creates a BufferDescriptor that references a CPU memory-buffer
      * @param buffer    Memory address of the CPU buffer to reference
      * @param size      Size of the CPU buffer in bytes
+     * @param handler   A custom handler for the callback
      * @param callback  A callback used to release the CPU buffer from this BufferDescriptor
      * @param user      An opaque user pointer passed to the callback function when it's called
      */
-    BufferDescriptor(void const* buffer, size_t size,
+    BufferDescriptor(void const* buffer, size_t const size,
-            CallbackHandler* handler, Callback callback, void* user = nullptr) noexcept
+            CallbackHandler* handler, Callback const callback, void* user = nullptr) noexcept
                 : buffer(const_cast<void*>(buffer)), size(size),
                 mCallback(callback), mUser(user), mHandler(handler) {
     }
@@ -116,8 +122,9 @@ public:
      *
      * @param buffer    Memory address of the CPU buffer to reference
      * @param size      Size of the CPU buffer in bytes
+     * @param data      A pointer to the data
      * @param handler   Handler to use to dispatch the callback, or nullptr for the default handler
-     * @return          a new BufferDescriptor
+     * @return          A new BufferDescriptor
      */
     template<typename T, void(T::*method)(void const*, size_t)>
     static BufferDescriptor make(void const* buffer, size_t size, T* data,
@@ -164,7 +171,7 @@ public:
      * @param callback  The new callback function
      * @param user      An opaque user pointer passed to the callbeck function when it's called
      */
-    void setCallback(Callback callback, void* user = nullptr) noexcept {
+    void setCallback(Callback const callback, void* user = nullptr) noexcept {
         this->mCallback = callback;
         this->mUser = user;
         this->mHandler = nullptr;
@@ -176,7 +183,7 @@ public:
      * @param callback  The new callback function
      * @param user      An opaque user pointer passed to the callbeck function when it's called
      */
-    void setCallback(CallbackHandler* handler, Callback callback, void* user = nullptr) noexcept {
+    void setCallback(CallbackHandler* handler, Callback const callback, void* user = nullptr) noexcept {
         mCallback = callback;
         mUser = user;
         mHandler = handler;

filament/backend/include/backend/DescriptorSetOffsetArray.h

@@ -19,8 +19,6 @@
 
 #include <backend/DriverApiForward.h>
 
-#include <utils/ostream.h>
-
 #include <initializer_list>
 #include <memory>
 
@@ -28,6 +26,10 @@
 #include <stdint.h>
 
 
+namespace utils::io {
+class ostream;
+} // namespace utils::io
+
 namespace filament::backend {
 
 void* allocateFromCommandStream(DriverApi& driver, size_t size, size_t alignment) noexcept;

filament/backend/include/backend/DriverEnums.h

@@ -25,21 +25,26 @@
 #include <backend/PresentCallable.h>
 
 #include <utils/BitmaskEnum.h>
+#include <utils/CString.h>
 #include <utils/FixedCapacityVector.h>
 #include <utils/Invocable.h>
-#include <utils/compiler.h>
+#include <utils/StaticString.h>
 #include <utils/debug.h>
-#include <utils/ostream.h>
 
 #include <math/vec4.h>
 
 #include <array>
 #include <type_traits>
 #include <variant>
+#include <string_view>
 
 #include <stddef.h>
 #include <stdint.h>
 
+namespace utils::io {
+class ostream;
+} // namespace utils::io
+
 /**
  * Types and enums used by filament's driver.
  *
@@ -158,7 +163,7 @@ enum class TimerQueryResult : int8_t {
     AVAILABLE = 1,  // result is available
 };
 
-static constexpr const char* backendToString(Backend backend) {
+constexpr std::string_view to_string(Backend const backend) noexcept {
     switch (backend) {
         case Backend::NOOP:
             return "Noop";
@@ -170,9 +175,10 @@ static constexpr const char* backendToString(Backend backend) {
             return "Metal";
         case Backend::WEBGPU:
             return "WebGPU";
-        default:
+        case Backend::DEFAULT:
-            return "Unknown";
+            return "Default";
     }
+    return "Unknown";
 }
 
 /**
@@ -189,7 +195,7 @@ enum class ShaderLanguage {
     WGSL = 5,
 };
 
-static constexpr const char* shaderLanguageToString(ShaderLanguage shaderLanguage) {
+constexpr const char* shaderLanguageToString(ShaderLanguage shaderLanguage) noexcept {
     switch (shaderLanguage) {
         case ShaderLanguage::ESSL1:
             return "ESSL 1.0";
@@ -204,6 +210,7 @@ static constexpr const char* shaderLanguageToString(ShaderLanguage shaderLanguag
         case ShaderLanguage::WGSL:
             return "WGSL";
     }
+    return "UNKNOWN";
 }
 
 enum class ShaderStage : uint8_t {
@@ -221,7 +228,7 @@ enum class ShaderStageFlags : uint8_t {
     ALL_SHADER_STAGE_FLAGS = VERTEX | FRAGMENT | COMPUTE
 };
 
-static inline constexpr bool hasShaderType(ShaderStageFlags flags, ShaderStage type) noexcept {
+constexpr bool hasShaderType(ShaderStageFlags flags, ShaderStage type) noexcept {
     switch (type) {
         case ShaderStage::VERTEX:
             return bool(uint8_t(flags) & uint8_t(ShaderStageFlags::VERTEX));
@@ -232,14 +239,239 @@ static inline constexpr bool hasShaderType(ShaderStageFlags flags, ShaderStage t
     }
 }
 
-enum class DescriptorType : uint8_t {
+enum class TextureType : uint8_t {
-    UNIFORM_BUFFER,
+    FLOAT,
-    SHADER_STORAGE_BUFFER,
+    INT,
-    SAMPLER,
+    UINT,
-    INPUT_ATTACHMENT,
+    DEPTH,
-    SAMPLER_EXTERNAL
+    STENCIL,
+    DEPTH_STENCIL
 };
 
+constexpr std::string_view to_string(TextureType type) noexcept {
+    switch (type) {
+        case TextureType::FLOAT:            return "FLOAT";
+        case TextureType::INT:              return "INT";
+        case TextureType::UINT:             return "UINT";
+        case TextureType::DEPTH:            return "DEPTH";
+        case TextureType::STENCIL:          return "STENCIL";
+        case TextureType::DEPTH_STENCIL:    return "DEPTH_STENCIL";
+    }
+    return "UNKNOWN";
+}
+
+ enum class DescriptorType : uint8_t {
+     SAMPLER_2D_FLOAT,
+     SAMPLER_2D_INT,
+     SAMPLER_2D_UINT,
+     SAMPLER_2D_DEPTH,
+
+     SAMPLER_2D_ARRAY_FLOAT,
+     SAMPLER_2D_ARRAY_INT,
+     SAMPLER_2D_ARRAY_UINT,
+     SAMPLER_2D_ARRAY_DEPTH,
+
+     SAMPLER_CUBE_FLOAT,
+     SAMPLER_CUBE_INT,
+     SAMPLER_CUBE_UINT,
+     SAMPLER_CUBE_DEPTH,
+
+     SAMPLER_CUBE_ARRAY_FLOAT,
+     SAMPLER_CUBE_ARRAY_INT,
+     SAMPLER_CUBE_ARRAY_UINT,
+     SAMPLER_CUBE_ARRAY_DEPTH,
+
+     SAMPLER_3D_FLOAT,
+     SAMPLER_3D_INT,
+     SAMPLER_3D_UINT,
+
+     SAMPLER_2D_MS_FLOAT,
+     SAMPLER_2D_MS_INT,
+     SAMPLER_2D_MS_UINT,
+
+     SAMPLER_2D_MS_ARRAY_FLOAT,
+     SAMPLER_2D_MS_ARRAY_INT,
+     SAMPLER_2D_MS_ARRAY_UINT,
+
+     SAMPLER_EXTERNAL,
+     UNIFORM_BUFFER,
+     SHADER_STORAGE_BUFFER,
+     INPUT_ATTACHMENT,
+ };
+
+constexpr bool isDepthDescriptor(DescriptorType const type) noexcept {
+    switch (type) {
+        case DescriptorType::SAMPLER_2D_DEPTH:
+        case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
+        case DescriptorType::SAMPLER_CUBE_DEPTH:
+        case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
+            return true;
+        default: ;
+    }
+    return false;
+}
+
+constexpr bool isFloatDescriptor(DescriptorType const type) noexcept {
+    switch (type) {
+        case DescriptorType::SAMPLER_2D_FLOAT:
+        case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
+        case DescriptorType::SAMPLER_CUBE_FLOAT:
+        case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
+        case DescriptorType::SAMPLER_3D_FLOAT:
+        case DescriptorType::SAMPLER_2D_MS_FLOAT:
+        case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
+            return true;
+        default: ;
+    }
+    return false;
+}
+
+constexpr bool isIntDescriptor(DescriptorType const type) noexcept {
+    switch (type) {
+        case DescriptorType::SAMPLER_2D_INT:
+        case DescriptorType::SAMPLER_2D_ARRAY_INT:
+        case DescriptorType::SAMPLER_CUBE_INT:
+        case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
+        case DescriptorType::SAMPLER_3D_INT:
+        case DescriptorType::SAMPLER_2D_MS_INT:
+        case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
+            return true;
+        default: ;
+    }
+    return false;
+}
+
+constexpr bool isUnsignedIntDescriptor(DescriptorType const type) noexcept {
+    switch (type) {
+        case DescriptorType::SAMPLER_2D_UINT:
+        case DescriptorType::SAMPLER_2D_ARRAY_UINT:
+        case DescriptorType::SAMPLER_CUBE_UINT:
+        case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
+        case DescriptorType::SAMPLER_3D_UINT:
+        case DescriptorType::SAMPLER_2D_MS_UINT:
+        case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
+            return true;
+        default: ;
+    }
+    return false;
+}
+
+constexpr bool is3dTypeDescriptor(DescriptorType const type) noexcept {
+    switch (type) {
+        case DescriptorType::SAMPLER_3D_FLOAT:
+        case DescriptorType::SAMPLER_3D_INT:
+        case DescriptorType::SAMPLER_3D_UINT:
+            return true;
+        default: ;
+    }
+    return false;
+}
+
+constexpr bool is2dTypeDescriptor(DescriptorType const type) noexcept {
+    switch (type) {
+        case DescriptorType::SAMPLER_2D_FLOAT:
+        case DescriptorType::SAMPLER_2D_INT:
+        case DescriptorType::SAMPLER_2D_UINT:
+        case DescriptorType::SAMPLER_2D_DEPTH:
+        case DescriptorType::SAMPLER_2D_MS_FLOAT:
+        case DescriptorType::SAMPLER_2D_MS_INT:
+        case DescriptorType::SAMPLER_2D_MS_UINT:
+            return true;
+        default: ;
+    }
+    return false;
+}
+
+constexpr bool is2dArrayTypeDescriptor(DescriptorType const type) noexcept {
+    switch (type) {
+        case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
+        case DescriptorType::SAMPLER_2D_ARRAY_INT:
+        case DescriptorType::SAMPLER_2D_ARRAY_UINT:
+        case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
+        case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
+        case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
+        case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
+            return true;
+        default: ;
+    }
+    return false;
+}
+
+constexpr bool isCubeTypeDescriptor(DescriptorType const type) noexcept {
+    switch (type) {
+        case DescriptorType::SAMPLER_CUBE_FLOAT:
+        case DescriptorType::SAMPLER_CUBE_INT:
+        case DescriptorType::SAMPLER_CUBE_UINT:
+        case DescriptorType::SAMPLER_CUBE_DEPTH:
+            return true;
+        default: ;
+    }
+    return false;
+}
+
+constexpr bool isCubeArrayTypeDescriptor(DescriptorType const type) noexcept {
+    switch (type) {
+        case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
+        case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
+        case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
+        case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
+            return true;
+        default: ;
+    }
+    return false;
+}
+
+constexpr bool isMultiSampledTypeDescriptor(DescriptorType const type) noexcept {
+    switch (type) {
+        case DescriptorType::SAMPLER_2D_MS_FLOAT:
+        case DescriptorType::SAMPLER_2D_MS_INT:
+        case DescriptorType::SAMPLER_2D_MS_UINT:
+        case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
+        case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
+        case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
+            return true;
+        default: ;
+    }
+    return false;
+}
+
+constexpr std::string_view to_string(DescriptorType type) noexcept {
+    #define DESCRIPTOR_TYPE_CASE(TYPE)  case DescriptorType::TYPE: return #TYPE;
+    switch (type) {
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_FLOAT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_INT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_UINT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_DEPTH)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_ARRAY_FLOAT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_ARRAY_INT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_ARRAY_UINT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_ARRAY_DEPTH)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_FLOAT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_INT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_UINT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_DEPTH)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_ARRAY_FLOAT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_ARRAY_INT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_ARRAY_UINT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_ARRAY_DEPTH)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_3D_FLOAT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_3D_INT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_3D_UINT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_MS_FLOAT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_MS_INT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_MS_UINT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_MS_ARRAY_FLOAT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_MS_ARRAY_INT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_MS_ARRAY_UINT)
+        DESCRIPTOR_TYPE_CASE(SAMPLER_EXTERNAL)
+        DESCRIPTOR_TYPE_CASE(UNIFORM_BUFFER)
+        DESCRIPTOR_TYPE_CASE(SHADER_STORAGE_BUFFER)
+        DESCRIPTOR_TYPE_CASE(INPUT_ATTACHMENT)
+    }
+    return "UNKNOWN";
+    #undef DESCRIPTOR_TYPE_CASE
+}
+
 enum class DescriptorFlags : uint8_t {
     NONE = 0x00,
     DYNAMIC_OFFSET = 0x01
@@ -250,6 +482,13 @@ using descriptor_set_t = uint8_t;
 using descriptor_binding_t = uint8_t;
 
 struct DescriptorSetLayoutBinding {
+    static bool isSampler(DescriptorType type) noexcept {
+        return int(type) <= int(DescriptorType::SAMPLER_EXTERNAL);
+    }
+    static bool isBuffer(DescriptorType type) noexcept {
+        return type == DescriptorType::UNIFORM_BUFFER ||
+               type == DescriptorType::SHADER_STORAGE_BUFFER;
+    }
     DescriptorType type;
     ShaderStageFlags stageFlags;
     descriptor_binding_t binding;
@@ -260,7 +499,7 @@ struct DescriptorSetLayoutBinding {
     //  no uninitialized padding bytes.
     //    uint8_t externalSamplerDataIndex = EXTERNAL_SAMPLER_DATA_INDEX_UNUSED;
 
-    friend inline bool operator==(DescriptorSetLayoutBinding const& lhs,
+    friend bool operator==(DescriptorSetLayoutBinding const& lhs,
             DescriptorSetLayoutBinding const& rhs) noexcept {
         return lhs.type == rhs.type &&
                lhs.flags == rhs.flags &&
@@ -293,7 +532,7 @@ enum class TargetBufferFlags : uint32_t {
     ALL = COLOR_ALL | DEPTH | STENCIL       //!< Color, depth and stencil buffer selected.
 };
 
-inline constexpr TargetBufferFlags getTargetBufferFlagsAt(size_t index) noexcept {
+constexpr TargetBufferFlags getTargetBufferFlagsAt(size_t index) noexcept {
     if (index == 0u) return TargetBufferFlags::COLOR0;
     if (index == 1u) return TargetBufferFlags::COLOR1;
     if (index == 2u) return TargetBufferFlags::COLOR2;
@@ -450,6 +689,24 @@ enum class SamplerType : uint8_t {
     SAMPLER_CUBEMAP_ARRAY,  //!< Cube map array texture (feature level 2)
 };
 
+constexpr std::string_view to_string(SamplerType const type) noexcept {
+    switch (type) {
+        case SamplerType::SAMPLER_2D:
+            return "SAMPLER_2D";
+        case SamplerType::SAMPLER_2D_ARRAY:
+            return "SAMPLER_2D_ARRAY";
+        case SamplerType::SAMPLER_CUBEMAP:
+            return "SAMPLER_CUBEMAP";
+        case SamplerType::SAMPLER_EXTERNAL:
+            return "SAMPLER_EXTERNAL";
+        case SamplerType::SAMPLER_3D:
+            return "SAMPLER_3D";
+        case SamplerType::SAMPLER_CUBEMAP_ARRAY:
+            return "SAMPLER_CUBEMAP_ARRAY";
+    }
+    return "Unknown";
+}
+
 //! Subpass type
 enum class SubpassType : uint8_t {
     SUBPASS_INPUT
@@ -463,6 +720,20 @@ enum class SamplerFormat : uint8_t {
     SHADOW = 3      //!< shadow sampler (PCF)
 };
 
+constexpr std::string_view to_string(SamplerFormat const format) noexcept {
+    switch (format) {
+        case SamplerFormat::INT:
+            return "INT";
+        case SamplerFormat::UINT:
+            return "UINT";
+        case SamplerFormat::FLOAT:
+            return "FLOAT";
+        case SamplerFormat::SHADOW:
+            return "SHADOW";
+    }
+    return "Unknown";
+}
+
 /**
  * Supported element types
  */
@@ -502,6 +773,15 @@ enum class BufferObjectBinding : uint8_t {
     SHADER_STORAGE
 };
 
+constexpr std::string_view to_string(BufferObjectBinding type) noexcept {
+    switch (type) {
+        case BufferObjectBinding::VERTEX:           return "VERTEX";
+        case BufferObjectBinding::UNIFORM:          return "UNIFORM";
+        case BufferObjectBinding::SHADER_STORAGE:   return "SHADER_STORAGE";
+    }
+    return "UNKNOWN";
+}
+
 //! Face culling Mode
 enum class CullingMode : uint8_t {
     NONE,               //!< No culling, front and back faces are visible
@@ -763,6 +1043,8 @@ enum class TextureFormat : uint16_t {
     SRGB_ALPHA_BPTC_UNORM,  // BC7 sRGB
 };
 
+TextureType getTextureType(TextureFormat format) noexcept;
+
 //! Bitmask describing the intended Texture Usage
 enum class TextureUsage : uint16_t {
     NONE                = 0x0000,
@@ -790,7 +1072,7 @@ enum class TextureSwizzle : uint8_t {
 };
 
 //! returns whether this format a depth format
-static constexpr bool isDepthFormat(TextureFormat format) noexcept {
+constexpr bool isDepthFormat(TextureFormat format) noexcept {
     switch (format) {
         case TextureFormat::DEPTH32F:
         case TextureFormat::DEPTH24:
@@ -803,7 +1085,7 @@ static constexpr bool isDepthFormat(TextureFormat format) noexcept {
     }
 }
 
-static constexpr bool isStencilFormat(TextureFormat format) noexcept {
+constexpr bool isStencilFormat(TextureFormat format) noexcept {
     switch (format) {
         case TextureFormat::STENCIL8:
         case TextureFormat::DEPTH24_STENCIL8:
@@ -814,7 +1096,7 @@ static constexpr bool isStencilFormat(TextureFormat format) noexcept {
     }
 }
 
-inline constexpr bool isColorFormat(TextureFormat format) noexcept {
+constexpr bool isColorFormat(TextureFormat format) noexcept {
     switch (format) {
         // Standard color formats
         case TextureFormat::R8:
@@ -841,7 +1123,7 @@ inline constexpr bool isColorFormat(TextureFormat format) noexcept {
     return false;
 }
 
-static constexpr bool isUnsignedIntFormat(TextureFormat format) {
+constexpr bool isUnsignedIntFormat(TextureFormat format) {
     switch (format) {
         case TextureFormat::R8UI:
         case TextureFormat::R16UI:
@@ -862,7 +1144,7 @@ static constexpr bool isUnsignedIntFormat(TextureFormat format) {
     }
 }
 
-static constexpr bool isSignedIntFormat(TextureFormat format) {
+constexpr bool isSignedIntFormat(TextureFormat format) {
     switch (format) {
         case TextureFormat::R8I:
         case TextureFormat::R16I:
@@ -884,35 +1166,35 @@ static constexpr bool isSignedIntFormat(TextureFormat format) {
 }
 
 //! returns whether this format is a compressed format
-static constexpr bool isCompressedFormat(TextureFormat format) noexcept {
+constexpr bool isCompressedFormat(TextureFormat format) noexcept {
     return format >= TextureFormat::EAC_R11;
 }
 
 //! returns whether this format is an ETC2 compressed format
-static constexpr bool isETC2Compression(TextureFormat format) noexcept {
+constexpr bool isETC2Compression(TextureFormat format) noexcept {
     return format >= TextureFormat::EAC_R11 && format <= TextureFormat::ETC2_EAC_SRGBA8;
 }
 
 //! returns whether this format is an S3TC compressed format
-static constexpr bool isS3TCCompression(TextureFormat format) noexcept {
+constexpr bool isS3TCCompression(TextureFormat format) noexcept {
     return format >= TextureFormat::DXT1_RGB && format <= TextureFormat::DXT5_SRGBA;
 }
 
-static constexpr bool isS3TCSRGBCompression(TextureFormat format) noexcept {
+constexpr bool isS3TCSRGBCompression(TextureFormat format) noexcept {
     return format >= TextureFormat::DXT1_SRGB && format <= TextureFormat::DXT5_SRGBA;
 }
 
 //! returns whether this format is an RGTC compressed format
-static constexpr bool isRGTCCompression(TextureFormat format) noexcept {
+constexpr bool isRGTCCompression(TextureFormat format) noexcept {
     return format >= TextureFormat::RED_RGTC1 && format <= TextureFormat::SIGNED_RED_GREEN_RGTC2;
 }
 
 //! returns whether this format is an BPTC compressed format
-static constexpr bool isBPTCCompression(TextureFormat format) noexcept {
+constexpr bool isBPTCCompression(TextureFormat format) noexcept {
     return format >= TextureFormat::RGB_BPTC_SIGNED_FLOAT && format <= TextureFormat::SRGB_ALPHA_BPTC_UNORM;
 }
 
-static constexpr bool isASTCCompression(TextureFormat format) noexcept {
+constexpr bool isASTCCompression(TextureFormat format) noexcept {
     return format >= TextureFormat::RGBA_ASTC_4x4 && format <= TextureFormat::SRGB8_ALPHA8_ASTC_12x12;
 }
 
@@ -1033,19 +1315,23 @@ struct SamplerParams {             // NOLINT
             assert_invariant(lhs.padding2 == 0);
             auto* pLhs = reinterpret_cast<uint32_t const*>(reinterpret_cast<char const*>(&lhs));
             auto* pRhs = reinterpret_cast<uint32_t const*>(reinterpret_cast<char const*>(&rhs));
-            return *pLhs == *pRhs;
+            return *pLhs < *pRhs;
         }
     };
 
+    bool isFiltered() const noexcept {
+        return filterMag != SamplerMagFilter::NEAREST || filterMin != SamplerMinFilter::NEAREST;
+    }
+
 private:
-    friend inline bool operator == (SamplerParams lhs, SamplerParams rhs) noexcept {
+    friend bool operator == (SamplerParams lhs, SamplerParams rhs) noexcept {
-        return SamplerParams::EqualTo{}(lhs, rhs);
+        return EqualTo{}(lhs, rhs);
     }
-    friend inline bool operator != (SamplerParams lhs, SamplerParams rhs) noexcept {
+    friend bool operator != (SamplerParams lhs, SamplerParams rhs) noexcept {
-        return  !SamplerParams::EqualTo{}(lhs, rhs);
+        return  !EqualTo{}(lhs, rhs);
     }
-    friend inline bool operator < (SamplerParams lhs, SamplerParams rhs) noexcept {
+    friend bool operator < (SamplerParams lhs, SamplerParams rhs) noexcept {
-        return SamplerParams::LessThan{}(lhs, rhs);
+        return LessThan{}(lhs, rhs);
     }
 };
 
@@ -1095,15 +1381,15 @@ struct SamplerYcbcrConversion {// NOLINT
     };
 
 private:
-    friend inline bool operator == (SamplerYcbcrConversion lhs, SamplerYcbcrConversion rhs)
+    friend bool operator == (SamplerYcbcrConversion lhs, SamplerYcbcrConversion rhs)
             noexcept {
         return SamplerYcbcrConversion::EqualTo{}(lhs, rhs);
     }
-    friend inline bool operator != (SamplerYcbcrConversion lhs, SamplerYcbcrConversion rhs)
+    friend bool operator != (SamplerYcbcrConversion lhs, SamplerYcbcrConversion rhs)
             noexcept {
         return  !SamplerYcbcrConversion::EqualTo{}(lhs, rhs);
     }
-    friend inline bool operator < (SamplerYcbcrConversion lhs, SamplerYcbcrConversion rhs)
+    friend bool operator < (SamplerYcbcrConversion lhs, SamplerYcbcrConversion rhs)
             noexcept {
         return SamplerYcbcrConversion::LessThan{}(lhs, rhs);
     }
@@ -1139,6 +1425,7 @@ struct ExternalSamplerDatum {
 static_assert(sizeof(ExternalSamplerDatum) == 12);
 
 struct DescriptorSetLayout {
+    std::variant<utils::StaticString, utils::CString, std::monostate> label;
     utils::FixedCapacityVector<DescriptorSetLayoutBinding> bindings;
 
 //  TODO: uncomment when needed

filament/backend/include/backend/Handle.h

@@ -17,9 +17,6 @@
 #ifndef TNT_FILAMENT_BACKEND_HANDLE_H
 #define TNT_FILAMENT_BACKEND_HANDLE_H
 
-#if !defined(NDEBUG)
-#include <utils/ostream.h>
-#endif
 #include <utils/debug.h>
 
 #include <type_traits> // FIXME: STL headers are not allowed in public headers
@@ -27,6 +24,10 @@
 
 #include <stdint.h>
 
+namespace utils::io {
+class ostream;
+} // namespace utils::io
+
 namespace filament::backend {
 
 struct HwBufferObject;

filament/backend/include/backend/PipelineState.h

@@ -20,12 +20,14 @@
 #include <backend/DriverEnums.h>
 #include <backend/Handle.h>
 
-#include <utils/ostream.h>
-
 #include <array>
 
 #include <stdint.h>
 
+namespace utils::io {
+class ostream;
+} // namespace utils::io
+
 namespace filament::backend {
 
 //! \privatesection

filament/backend/include/backend/PixelBufferDescriptor.h

@@ -24,11 +24,14 @@
 
 #include <utils/compiler.h>
 #include <utils/debug.h>
-#include <utils/ostream.h>
 
 #include <stddef.h>
 #include <stdint.h>
 
+namespace utils::io {
+class ostream;
+} // namespace utils::io
+
 namespace filament::backend {
 
 /**
@@ -201,23 +204,15 @@ public:
                 }, new T(std::forward<T>(functor))
         };
     }
-
-    // --------------------------------------------------------------------------------------------
-
     /**
-     * Computes the size in bytes needed to fit an image of given dimensions and format
+     * Computes the size in bytes for a pixel of given dimensions and format
      *
      * @param format    Format of the image pixels
      * @param type      Type of the image pixels
-     * @param stride    Stride of a row in pixels
+     * @return The size of the specified pixel in bytes
-     * @param height    Height of the image in rows
-     * @param alignment Alignment in bytes of pixel rows
-     * @return The buffer size needed to fit this image in bytes
      */
-    static constexpr size_t computeDataSize(PixelDataFormat format, PixelDataType type,
-            size_t stride, size_t height, size_t alignment) noexcept {
-        assert_invariant(alignment);
 
+    static constexpr size_t computePixelSize(PixelDataFormat format, PixelDataType type) noexcept {
         if (type == PixelDataType::COMPRESSED) {
             return 0;
         }
@@ -239,7 +234,7 @@ public:
             case PixelDataFormat::RGB_INTEGER:
                 n = 3;
                 break;
-            case PixelDataFormat::UNUSED: // shouldn't happen (used to be rgbm)
+            case PixelDataFormat::UNUSED:// shouldn't happen (used to be rgbm)
             case PixelDataFormat::RGBA:
             case PixelDataFormat::RGBA_INTEGER:
                 n = 4;
@@ -248,7 +243,7 @@ public:
 
         size_t bpp = n;
         switch (type) {
-            case PixelDataType::COMPRESSED: // Impossible -- to squash the IDE warnings
+            case PixelDataType::COMPRESSED:// Impossible -- to squash the IDE warnings
             case PixelDataType::UBYTE:
             case PixelDataType::BYTE:
                 // nothing to do
@@ -279,16 +274,35 @@ public:
                 bpp = 2;
                 break;
         }
+        return bpp;
+    }
 
+    // --------------------------------------------------------------------------------------------
+
+    /**
+     * Computes the size in bytes needed to fit an image of given dimensions and format
+     *
+     * @param format    Format of the image pixels
+     * @param type      Type of the image pixels
+     * @param stride    Stride of a row in pixels
+     * @param height    Height of the image in rows
+     * @param alignment Alignment in bytes of pixel rows
+     * @return The buffer size needed to fit this image in bytes
+     */
+    static constexpr size_t computeDataSize(PixelDataFormat format, PixelDataType type,
+            size_t stride, size_t height, size_t alignment) noexcept {
+        assert_invariant(alignment);
+
+        size_t bpp = computePixelSize(format, type);
         size_t const bpr = bpp * stride;
         size_t const bprAligned = (bpr + (alignment - 1)) & (~alignment + 1);
         return bprAligned * height;
     }
 
     //! left coordinate in pixels
-    uint32_t left   = 0;
+    uint32_t left = 0;
     //! top coordinate in pixels
-    uint32_t top    = 0;
+    uint32_t top = 0;
     union {
         struct {
             //! stride in pixels

filament/backend/include/backend/Program.h

@@ -20,12 +20,10 @@
 #include <utils/CString.h>
 #include <utils/FixedCapacityVector.h>
 #include <utils/Invocable.h>
-#include <utils/ostream.h>
 
 #include <backend/DriverEnums.h>
 
 #include <array>
-#include <unordered_map>
 #include <tuple>
 #include <utility>
 #include <variant>
@@ -33,6 +31,10 @@
 #include <stddef.h>
 #include <stdint.h>
 
+namespace utils::io {
+class ostream;
+} // namespace utils::io
+
 namespace filament::backend {
 
 class Program {
@@ -44,8 +46,8 @@ public:
 
     struct Descriptor {
         utils::CString name;
-        backend::DescriptorType type;
+        DescriptorType type;
-        backend::descriptor_binding_t binding;
+        descriptor_binding_t binding;
     };
 
     struct SpecializationConstant {

filament/backend/include/backend/TargetBufferInfo.h

@@ -19,22 +19,26 @@
 
 #include <backend/Handle.h>
 
-#include <utils/ostream.h>
+#include <utility>
 
 #include <stddef.h>
 #include <stdint.h>
 
+namespace utils::io {
+class ostream;
+} // namespace utils::io
+
 namespace filament::backend {
 
 //! \privatesection
 
 struct TargetBufferInfo {
     // note: the parameters of this constructor are not in the order of this structure's fields
-    TargetBufferInfo(Handle<HwTexture> handle, uint8_t level, uint16_t layer) noexcept
+    TargetBufferInfo(Handle<HwTexture> handle, uint8_t const level, uint16_t const layer) noexcept
-            : handle(handle), level(level), layer(layer) {
+            : handle(std::move(handle)), level(level), layer(layer) {
     }
 
-    TargetBufferInfo(Handle<HwTexture> handle, uint8_t level) noexcept
+    TargetBufferInfo(Handle<HwTexture> handle, uint8_t const level) noexcept
             : handle(handle), level(level) {
     }
 
@@ -70,11 +74,11 @@ private:
     TargetBufferInfo mInfos[MAX_SUPPORTED_RENDER_TARGET_COUNT];
 
 public:
-    TargetBufferInfo const& operator[](size_t i) const noexcept {
+    TargetBufferInfo const& operator[](size_t const i) const noexcept {
         return mInfos[i];
     }
 
-    TargetBufferInfo& operator[](size_t i) noexcept {
+    TargetBufferInfo& operator[](size_t const i) noexcept {
         return mInfos[i];
     }
 

filament/backend/include/backend/platforms/PlatformMetal.h

@@ -39,18 +39,40 @@ public:
     Driver* createDriver(void* sharedContext, const Platform::DriverConfig& driverConfig) noexcept override;
     int getOSVersion() const noexcept override { return 0; }
 
+    /**
+     * Optionally initializes the Metal platform by acquiring resources necessary for rendering.
+     *
+     * This method attempts to acquire a Metal device and command queue, returning true if both are
+     * successfully obtained, or false otherwise. Typically, these objects are acquired when
+     * the Metal backend is initialized. This method allows clients to check for their availability
+     * earlier.
+     *
+     * Calling initialize() is optional and safe to do so multiple times. After initialize() returns
+     * true, subsequent calls will continue to return true but have no effect.
+     *
+     * initialize() must be called from the main thread.
+     *
+     * @returns true if the device and command queue have been successfully obtained; false
+     * otherwise.
+     */
+    bool initialize() noexcept;
+
     /**
      * Obtain the preferred Metal device object for the backend to use.
      *
      * On desktop platforms, there may be multiple GPUs suitable for rendering, and this method is
      * free to decide which one to use. On mobile systems with a single GPU, implementations should
      * simply return the result of MTLCreateSystemDefaultDevice();
+     *
+     * createDevice is called by the Metal backend from the backend thread.
      */
     virtual void createDevice(MetalDevice& outDevice) noexcept;
 
     /**
      * Create a command submission queue on the Metal device object.
      *
+     * createCommandQueue is called by the Metal backend from the backend thread.
+     *
      * @param device The device which was returned from createDevice()
      */
     virtual void createCommandQueue(
@@ -60,6 +82,8 @@ public:
      * Obtain a MTLCommandBuffer enqueued on this Platform's MTLCommandQueue. The command buffer is
      * guaranteed to execute before all subsequent command buffers created either by Filament, or
      * further calls to this method.
+     *
+     * createAndEnqueueCommandBuffer must be called from the main thread.
      */
     void createAndEnqueueCommandBuffer(MetalCommandBuffer& outCommandBuffer) noexcept;
 
@@ -68,6 +92,8 @@ public:
      *
      * Each frame rendered requires a CAMetalDrawable texture, which is presented on-screen at the
      * completion of each frame. These are limited and provided round-robin style by the system.
+     *
+     * setDrawableFailureBehavior must be called from the main thread.
      */
     enum class DrawableFailureBehavior : uint8_t {
         /**

filament/backend/include/backend/platforms/VulkanPlatform.h

@@ -27,8 +27,11 @@
 #include <utils/Hash.h>
 #include <utils/PrivateImplementation.h>
 
+#include <cstddef>
+#include <functional>
 #include <tuple>
 #include <unordered_set>
+#include <string>
 
 #include <stddef.h>
 #include <stdint.h>

filament/backend/src/BackendUtils.cpp

@@ -18,6 +18,8 @@
 
 #include "DataReshaper.h"
 
+#include <backend/DriverEnums.h>
+
 #include <utils/CString.h>
 
 #include <string_view>
@@ -223,6 +225,143 @@ size_t getFormatSize(TextureFormat format) noexcept {
     }
 }
 
+TextureType getTextureType(TextureFormat const format) noexcept {
+    switch (format) {
+        case TextureFormat::UNUSED:
+            // should not happen
+            return TextureType::FLOAT;
+
+        case TextureFormat::R8:
+        case TextureFormat::R16F:
+        case TextureFormat::RG8:
+        case TextureFormat::RGB565:
+        case TextureFormat::RGB5_A1:
+        case TextureFormat::RGBA4:
+        case TextureFormat::R32F:
+        case TextureFormat::RGB8:
+        case TextureFormat::SRGB8:
+        case TextureFormat::RG16F:
+        case TextureFormat::R11F_G11F_B10F:
+        case TextureFormat::RGB9_E5:
+        case TextureFormat::RGBA8:
+        case TextureFormat::SRGB8_A8:
+        case TextureFormat::RGB10_A2:
+        case TextureFormat::RGB16F:
+        case TextureFormat::RG32F:
+        case TextureFormat::RGBA16F:
+        case TextureFormat::RGB32F:
+        case TextureFormat::RGBA32F:
+            return TextureType::FLOAT;
+
+        case TextureFormat::R8_SNORM:
+        case TextureFormat::RG8_SNORM:
+        case TextureFormat::RGB8_SNORM:
+        case TextureFormat::RGBA8_SNORM:
+            // SNORM are treated as float
+            return TextureType::FLOAT;
+
+        case TextureFormat::R8UI:
+        case TextureFormat::R16UI:
+        case TextureFormat::RG8UI:
+        case TextureFormat::RGB8UI:
+        case TextureFormat::R32UI:
+        case TextureFormat::RG16UI:
+        case TextureFormat::RGBA8UI:
+        case TextureFormat::RGB16UI:
+        case TextureFormat::RG32UI:
+        case TextureFormat::RGBA16UI:
+        case TextureFormat::RGB32UI:
+        case TextureFormat::RGBA32UI:
+            return TextureType::UINT;
+
+        case TextureFormat::R8I:
+        case TextureFormat::R16I:
+        case TextureFormat::RG8I:
+        case TextureFormat::RGB8I:
+        case TextureFormat::R32I:
+        case TextureFormat::RG16I:
+        case TextureFormat::RGBA8I:
+        case TextureFormat::RGB16I:
+        case TextureFormat::RG32I:
+        case TextureFormat::RGBA16I:
+        case TextureFormat::RGB32I:
+        case TextureFormat::RGBA32I:
+            return TextureType::INT;
+
+        case TextureFormat::DEPTH16:
+        case TextureFormat::DEPTH24:
+        case TextureFormat::DEPTH32F:
+            return TextureType::DEPTH;
+
+        case TextureFormat::STENCIL8:
+            return TextureType::STENCIL;
+
+        case TextureFormat::DEPTH24_STENCIL8:
+        case TextureFormat::DEPTH32F_STENCIL8:
+            return TextureType::DEPTH_STENCIL;
+
+        // Compressed formats ---------------------------------------------------------------------
+
+        case TextureFormat::EAC_RG11:
+        case TextureFormat::EAC_RG11_SIGNED:
+        case TextureFormat::ETC2_EAC_RGBA8:
+        case TextureFormat::ETC2_EAC_SRGBA8:
+        case TextureFormat::EAC_R11:
+        case TextureFormat::EAC_R11_SIGNED:
+        case TextureFormat::ETC2_RGB8:
+        case TextureFormat::ETC2_SRGB8:
+        case TextureFormat::ETC2_RGB8_A1:
+        case TextureFormat::ETC2_SRGB8_A1:
+        case TextureFormat::DXT1_RGB:
+        case TextureFormat::DXT1_RGBA:
+        case TextureFormat::DXT1_SRGB:
+        case TextureFormat::DXT1_SRGBA:
+        case TextureFormat::DXT3_RGBA:
+        case TextureFormat::DXT3_SRGBA:
+        case TextureFormat::DXT5_RGBA:
+        case TextureFormat::DXT5_SRGBA:
+        case TextureFormat::RED_RGTC1:
+        case TextureFormat::SIGNED_RED_RGTC1:
+        case TextureFormat::RED_GREEN_RGTC2:
+        case TextureFormat::SIGNED_RED_GREEN_RGTC2:
+        case TextureFormat::RGB_BPTC_SIGNED_FLOAT:
+        case TextureFormat::RGB_BPTC_UNSIGNED_FLOAT:
+        case TextureFormat::RGBA_BPTC_UNORM:
+        case TextureFormat::SRGB_ALPHA_BPTC_UNORM:
+        case TextureFormat::RGBA_ASTC_4x4:
+        case TextureFormat::RGBA_ASTC_5x4:
+        case TextureFormat::RGBA_ASTC_5x5:
+        case TextureFormat::RGBA_ASTC_6x5:
+        case TextureFormat::RGBA_ASTC_6x6:
+        case TextureFormat::RGBA_ASTC_8x5:
+        case TextureFormat::RGBA_ASTC_8x6:
+        case TextureFormat::RGBA_ASTC_8x8:
+        case TextureFormat::RGBA_ASTC_10x5:
+        case TextureFormat::RGBA_ASTC_10x6:
+        case TextureFormat::RGBA_ASTC_10x8:
+        case TextureFormat::RGBA_ASTC_10x10:
+        case TextureFormat::RGBA_ASTC_12x10:
+        case TextureFormat::RGBA_ASTC_12x12:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_4x4:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_5x4:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_5x5:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_6x5:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_6x6:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_8x5:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_8x6:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_8x8:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_10x5:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_10x6:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_10x8:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_10x10:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_12x10:
+        case TextureFormat::SRGB8_ALPHA8_ASTC_12x12:
+            return TextureType::FLOAT;
+    }
+
+    return TextureType::FLOAT;
+}
+
 size_t getFormatComponentCount(TextureFormat format) noexcept {
     switch (format) {
         case TextureFormat::R8:

filament/backend/src/CommandBufferQueue.cpp

@@ -18,12 +18,13 @@
 #include "private/backend/CircularBuffer.h"
 #include "private/backend/CommandStream.h"
 
+#include <private/utils/Tracing.h>
+
 #include <utils/compiler.h>
 #include <utils/Log.h>
 #include <utils/Mutex.h>
 #include <utils/ostream.h>
 #include <utils/Panic.h>
-#include <utils/Systrace.h>
 #include <utils/debug.h>
 
 #include <algorithm>
@@ -79,7 +80,7 @@ bool CommandBufferQueue::isExitRequested() const {
 
 
 void CommandBufferQueue::flush() noexcept {
-    SYSTRACE_CALL();
+    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
 
     CircularBuffer& circularBuffer = mCircularBuffer;
     if (circularBuffer.empty()) {
@@ -129,7 +130,7 @@ void CommandBufferQueue::flush() noexcept {
         mHighWatermark = std::max(mHighWatermark, totalUsed);
 #endif
 
-        SYSTRACE_NAME("waiting: CircularBuffer::flush()");
+        FILAMENT_TRACING_NAME(FILAMENT_TRACING_CATEGORY_FILAMENT, "waiting: CircularBuffer::flush()");
 
         FILAMENT_CHECK_POSTCONDITION(!mPaused) <<
                 "CommandStream is full, but since the rendering thread is paused, "

filament/backend/src/CommandStream.cpp

@@ -16,6 +16,8 @@
 
 #include "private/backend/CommandStream.h"
 
+#include <private/utils/Tracing.h>
+
 #if DEBUG_COMMAND_STREAM
 #include <utils/CallStack.h>
 #endif
@@ -24,7 +26,6 @@
 #include <utils/Log.h>
 #include <utils/ostream.h>
 #include <utils/Profiler.h>
-#include <utils/Systrace.h>
 
 #include <cstddef>
 #include <functional>
@@ -79,12 +80,13 @@ CommandStream::CommandStream(Driver& driver, CircularBuffer& buffer) noexcept
 }
 
 void CommandStream::execute(void* buffer) {
-    // NOTE: we can't use SYSTRACE_CALL() or similar here because, execute() below, also
+    // NOTE: we can't use FILAMENT_TRACING_CALL() or similar here because, execute() below, also
     // uses systrace BEGIN/END and the END is not guaranteed to be happening in this scope.
 
     Profiler profiler;
 
-    if constexpr (SYSTRACE_TAG) {
+
+    if constexpr (FILAMENT_TRACING_ENABLED) {
         if (UTILS_UNLIKELY(mUsePerformanceCounter)) {
             // we want to remove all this when tracing is completely disabled
             profiler.resetEvents(Profiler::EV_CPU_CYCLES  | Profiler::EV_BPU_MISSES);
@@ -100,17 +102,17 @@ void CommandStream::execute(void* buffer) {
         }
     });
 
-    if constexpr (SYSTRACE_TAG) {
+    if constexpr (FILAMENT_TRACING_ENABLED) {
         if (UTILS_UNLIKELY(mUsePerformanceCounter)) {
             // we want to remove all this when tracing is completely disabled
             profiler.stop();
             UTILS_UNUSED Profiler::Counters const counters = profiler.readCounters();
-            SYSTRACE_CONTEXT();
+            FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-            SYSTRACE_VALUE32("GLThread (I)", counters.getInstructions());
+            FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "GLThread (I)", counters.getInstructions());
-            SYSTRACE_VALUE32("GLThread (C)", counters.getCpuCycles());
+            FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "GLThread (C)", counters.getCpuCycles());
-            SYSTRACE_VALUE32("GLThread (CPI x10)", counters.getCPI() * 10);
+            FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "GLThread (CPI x10)", counters.getCPI() * 10);
-            SYSTRACE_VALUE32("GLThread (BPU miss)", counters.getBranchMisses());
+            FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "GLThread (BPU miss)", counters.getBranchMisses());
-            SYSTRACE_VALUE32("GLThread (I / BPU miss)",
+            FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "GLThread (I / BPU miss)",
                     counters.getInstructions() / counters.getBranchMisses());
         }
     }

filament/backend/src/CommandStreamDispatcher.h

@@ -20,8 +20,9 @@
 #include "private/backend/Driver.h"
 #include "private/backend/CommandStream.h"
 
+#include <private/utils/Tracing.h>
+
 #include <utils/compiler.h>
-#include <utils/Systrace.h>
 
 #include <utility>
 
@@ -38,7 +39,7 @@
 #if DEBUG_LEVEL == DEBUG_LEVEL_NONE
 #   define SYSTRACE()
 #elif DEBUG_LEVEL == DEBUG_LEVEL_SYSTRACE
-#   define SYSTRACE() SYSTRACE_CALL();
+#   define SYSTRACE() FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
 #else
 #   error "invalid debug level"
 #endif

filament/backend/src/CompilerThreadPool.cpp

@@ -16,7 +16,7 @@
 
 #include "CompilerThreadPool.h"
 
-#include <utils/Systrace.h>
+#include <private/utils/Tracing.h>
 
 #include <memory>
 
@@ -41,7 +41,7 @@ void CompilerThreadPool::init(uint32_t threadCount,
 
     for (size_t i = 0; i < threadCount; i++) {
         mCompilerThreads.emplace_back([this, setup, cleanup]() {
-            SYSTRACE_CONTEXT();
+            FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
 
             (*setup)();
 
@@ -54,7 +54,7 @@ void CompilerThreadPool::init(uint32_t threadCount,
                                     [](auto&& q) { return q.empty(); }));
                 });
 
-                SYSTRACE_VALUE32("CompilerThreadPool Jobs",
+                FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "CompilerThreadPool Jobs",
                         mQueues[0].size() + mQueues[1].size());
 
                 if (UTILS_LIKELY(!mExitRequested)) {

filament/backend/src/Driver.cpp

@@ -23,11 +23,12 @@
 #include <backend/BufferDescriptor.h>
 #include <backend/DriverEnums.h>
 
+#include <private/utils/Tracing.h>
+
 #include <utils/compiler.h>
 #include <utils/debug.h>
 #include <utils/Log.h>
 #include <utils/ostream.h>
-#include <utils/Systrace.h>
 
 #include <math/half.h>
 #include <math/vec2.h>
@@ -151,30 +152,31 @@ void DriverBase::debugCommandBegin(CommandStream* cmds, bool synchronous, const
             utils::slog.d << methodName << utils::io::endl;
         }
         if constexpr (bool(FILAMENT_DEBUG_COMMANDS & FILAMENT_DEBUG_COMMANDS_SYSTRACE)) {
-            SYSTRACE_CONTEXT();
+            FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-            SYSTRACE_NAME_BEGIN(methodName);
+            FILAMENT_TRACING_NAME_BEGIN(FILAMENT_TRACING_CATEGORY_FILAMENT, methodName);
 
             if (!synchronous) {
                 cmds->queueCommand([=]() {
-                    SYSTRACE_CONTEXT();
+                    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-                    SYSTRACE_NAME_BEGIN(methodName);
+                    FILAMENT_TRACING_NAME_BEGIN(FILAMENT_TRACING_CATEGORY_FILAMENT, methodName);
                 });
             }
         }
     }
 }
 
-void DriverBase::debugCommandEnd(CommandStream* cmds, bool synchronous, const char* methodName) noexcept {
+void DriverBase::debugCommandEnd(CommandStream* cmds, bool synchronous,
+        const char* methodName) noexcept {
     if constexpr (bool(FILAMENT_DEBUG_COMMANDS > FILAMENT_DEBUG_COMMANDS_NONE)) {
         if constexpr (bool(FILAMENT_DEBUG_COMMANDS & FILAMENT_DEBUG_COMMANDS_SYSTRACE)) {
             if (!synchronous) {
                 cmds->queueCommand([]() {
-                    SYSTRACE_CONTEXT();
+                    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-                    SYSTRACE_NAME_END();
+                    FILAMENT_TRACING_NAME_END(FILAMENT_TRACING_CATEGORY_FILAMENT);
                 });
             }
-            SYSTRACE_CONTEXT();
+            FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-            SYSTRACE_NAME_END();
+            FILAMENT_TRACING_NAME_END(FILAMENT_TRACING_CATEGORY_FILAMENT);
         }
     }
 }

filament/backend/src/Platform.cpp

@@ -17,6 +17,7 @@
 #include <backend/Platform.h>
 
 #include <utils/compiler.h>
+#include <utils/ostream.h>
 
 #include <atomic>
 #include <utility>

filament/backend/src/PlatformFactory.cpp

@@ -16,7 +16,8 @@
 
 #include <private/backend/PlatformFactory.h>
 
-#include <utils/Systrace.h>
+#include <private/utils/Tracing.h>
+
 #include <utils/debug.h>
 
 // We need to keep this up top for the linux (X11) name collisions.
@@ -85,7 +86,7 @@ namespace filament::backend {
 // responsible for destroying it. Initialization of the backend API is deferred until
 // createDriver(). The passed-in backend hint is replaced with the resolved backend.
 Platform* PlatformFactory::create(Backend* backend) noexcept {
-    SYSTRACE_CALL();
+    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
     assert_invariant(backend);
 
 #if defined(__ANDROID__)

filament/backend/src/SystraceProfile.h

@@ -17,7 +17,7 @@
 #ifndef TNT_FILAMENT_BACKEND_SYSTRACEPROFILE_H
 #define TNT_FILAMENT_BACKEND_SYSTRACEPROFILE_H
 
-#include <utils/Systrace.h>
+#include <private/utils/Tracing.h>
 
 #define PROFILE_SCOPE(marker)       SYSTRACE_NAME(marker)
 

filament/backend/src/metal/MetalBuffer.mm

@@ -19,6 +19,8 @@
 
 #include "MetalContext.h"
 
+#include <utils/Panic.h>
+
 namespace filament {
 namespace backend {
 

filament/backend/src/metal/MetalDriver.mm

@@ -672,22 +672,8 @@ void MetalDriver::createTimerQueryR(Handle<HwTimerQuery> tqh, int) {
     // nothing to do, timer query was constructed in createTimerQueryS
 }
 
-const char* toString(DescriptorType type) {
+UTILS_UNUSED
-    switch (type) {
+static const char* toString(ShaderStageFlags flags) {
-        case DescriptorType::UNIFORM_BUFFER:
-            return "UNIFORM_BUFFER";
-        case DescriptorType::SHADER_STORAGE_BUFFER:
-            return "SHADER_STORAGE_BUFFER";
-        case DescriptorType::SAMPLER:
-            return "SAMPLER";
-        case DescriptorType::INPUT_ATTACHMENT:
-            return "INPUT_ATTACHMENT";
-        case DescriptorType::SAMPLER_EXTERNAL:
-            return "SAMPLER_EXTERNAL";
-    }
-}
-
-const char* toString(ShaderStageFlags flags) {
     std::vector<const char*> stages;
     if (any(flags & ShaderStageFlags::VERTEX)) {
         stages.push_back("VERTEX");
@@ -721,15 +707,25 @@ const char* toString(DescriptorFlags flags) {
 
 void MetalDriver::createDescriptorSetLayoutR(
         Handle<HwDescriptorSetLayout> dslh, DescriptorSetLayout&& info) {
+#if FILAMENT_METAL_DEBUG_LOG == 1
+    const char* labelStr = "";
+    std::visit([&labelStr](auto&& arg) {
+        using T = std::decay_t<decltype(arg)>;
+        if constexpr (std::is_same_v<T, utils::CString> || std::is_same_v<T, utils::StaticString>) {
+            labelStr = arg.c_str();
+        }
+    }, info.label);
     std::sort(info.bindings.begin(), info.bindings.end(),
             [](const auto& a, const auto& b) { return a.binding < b.binding; });
-    DEBUG_LOG("createDescriptorSetLayoutR(dslh = %d, info = {\n", dslh.getId());
+    DEBUG_LOG("createDescriptorSetLayoutR(dslh = %d, info = { label = %s,\n", dslh.getId(),
+            labelStr);
     for (size_t i = 0; i < info.bindings.size(); i++) {
         DEBUG_LOG("    {binding = %d, type = %s, count = %d, stage = %s, flags = %s},\n",
                 info.bindings[i].binding, toString(info.bindings[i].type), info.bindings[i].count,
                 toString(info.bindings[i].stageFlags), toString(info.bindings[i].flags));
     }
     DEBUG_LOG("})\n");
+#endif
     construct_handle<MetalDescriptorSetLayout>(dslh, std::move(info));
 }
 

filament/backend/src/metal/MetalEnums.h

@@ -185,6 +185,7 @@ inline MTLPixelFormat getMetalFormat(PixelDataFormat format, PixelDataType type)
     CONVERT(RGBA_INTEGER, UINT, RGBA32Uint);
     CONVERT(RGBA_INTEGER, INT, RGBA32Sint);
     CONVERT(RGBA, FLOAT, RGBA32Float);
+    CONVERT(DEPTH_COMPONENT, FLOAT, Depth32Float);
     #undef CONVERT
 
     return MTLPixelFormatInvalid;

filament/backend/src/metal/MetalHandles.mm

@@ -1356,7 +1356,31 @@ id<MTLArgumentEncoder> MetalDescriptorSetLayout::getArgumentEncoderSlow(id<MTLDe
                 [arguments addObject:bufferArgument];
                 break;
             }
-            case DescriptorType::SAMPLER:
+            case DescriptorType::SAMPLER_2D_FLOAT:
+            case DescriptorType::SAMPLER_2D_INT:
+            case DescriptorType::SAMPLER_2D_UINT:
+            case DescriptorType::SAMPLER_2D_DEPTH:
+            case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_2D_ARRAY_INT:
+            case DescriptorType::SAMPLER_2D_ARRAY_UINT:
+            case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
+            case DescriptorType::SAMPLER_CUBE_FLOAT:
+            case DescriptorType::SAMPLER_CUBE_INT:
+            case DescriptorType::SAMPLER_CUBE_UINT:
+            case DescriptorType::SAMPLER_CUBE_DEPTH:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
+            case DescriptorType::SAMPLER_3D_FLOAT:
+            case DescriptorType::SAMPLER_3D_INT:
+            case DescriptorType::SAMPLER_3D_UINT:
+            case DescriptorType::SAMPLER_2D_MS_FLOAT:
+            case DescriptorType::SAMPLER_2D_MS_INT:
+            case DescriptorType::SAMPLER_2D_MS_UINT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
             case DescriptorType::SAMPLER_EXTERNAL: {
                 MTLArgumentDescriptor* textureArgument = [MTLArgumentDescriptor argumentDescriptor];
                 textureArgument.index = binding.binding * 2;
@@ -1382,6 +1406,9 @@ id<MTLArgumentEncoder> MetalDescriptorSetLayout::getArgumentEncoderSlow(id<MTLDe
                 break;
         }
     }
+    if (arguments.count == 0) {
+        return nil;
+    }
     return [device newArgumentEncoderWithArguments:arguments];
 }
 
@@ -1442,6 +1469,9 @@ id<MTLBuffer> MetalDescriptorSet::finalizeAndGetBuffer(MetalDriver* driver, Shad
 
     id<MTLArgumentEncoder> encoder =
             layout->getArgumentEncoder(context.device, stage, textureTypes);
+    if (!encoder) {
+        return nil;
+    }
 
     {
         ScopedAllocationTimer timer("descriptor_set");
@@ -1472,7 +1502,31 @@ id<MTLBuffer> MetalDescriptorSet::finalizeAndGetBuffer(MetalDriver* driver, Shad
                            atIndex:binding.binding * 2];
                 break;
             }
-            case DescriptorType::SAMPLER:
+            case DescriptorType::SAMPLER_2D_FLOAT:
+            case DescriptorType::SAMPLER_2D_INT:
+            case DescriptorType::SAMPLER_2D_UINT:
+            case DescriptorType::SAMPLER_2D_DEPTH:
+            case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_2D_ARRAY_INT:
+            case DescriptorType::SAMPLER_2D_ARRAY_UINT:
+            case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
+            case DescriptorType::SAMPLER_CUBE_FLOAT:
+            case DescriptorType::SAMPLER_CUBE_INT:
+            case DescriptorType::SAMPLER_CUBE_UINT:
+            case DescriptorType::SAMPLER_CUBE_DEPTH:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
+            case DescriptorType::SAMPLER_3D_FLOAT:
+            case DescriptorType::SAMPLER_3D_INT:
+            case DescriptorType::SAMPLER_3D_UINT:
+            case DescriptorType::SAMPLER_2D_MS_FLOAT:
+            case DescriptorType::SAMPLER_2D_MS_INT:
+            case DescriptorType::SAMPLER_2D_MS_UINT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
             case DescriptorType::SAMPLER_EXTERNAL: {
                 auto found = textures.find(binding.binding);
                 if (found == textures.end()) {

filament/backend/src/metal/MetalState.h

@@ -20,18 +20,19 @@
 #include <Metal/Metal.h>
 
 #include "private/backend/Driver.h"
-#include "backend/Program.h"
 
 #include <backend/DriverEnums.h>
+#include <backend/Program.h>
 
+#include <utils/bitset.h>
 #include <utils/FixedCapacityVector.h>
-
-#include <memory>
-#include <tsl/robin_map.h>
-
 #include <utils/Hash.h>
 #include <utils/Invocable.h>
 
+#include <tsl/robin_map.h>
+
+#include <memory>
+
 namespace filament {
 namespace backend {
 

filament/backend/src/metal/PlatformMetal.mm

@@ -24,14 +24,22 @@
 #import <Foundation/Foundation.h>
 
 #include <atomic>
+#include <mutex>
 
 namespace filament::backend {
 
 struct PlatformMetalImpl {
+    std::mutex mLock;   // locks mDevice and mCommandQueue
+    id<MTLDevice> mDevice = nil;
     id<MTLCommandQueue> mCommandQueue = nil;
+
     // read form driver thread, read/written to from client thread
     std::atomic<PlatformMetal::DrawableFailureBehavior> mDrawableFailureBehavior =
             PlatformMetal::DrawableFailureBehavior::PANIC;
+
+    // These methods must be called with mLock held
+    void createDeviceImpl(MetalDevice& outDevice);
+    void createCommandQueueImpl(MetalDevice& device, MetalCommandQueue& outCommandQueue);
 };
 
 Platform* createDefaultMetalPlatform() {
@@ -48,7 +56,59 @@ Driver* PlatformMetal::createDriver(void* /*sharedContext*/, const Platform::Dri
     return MetalDriverFactory::create(this, driverConfig);
 }
 
+
+bool PlatformMetal::initialize() noexcept {
+    std::lock_guard<std::mutex> lock(pImpl->mLock);
+
+    MetalDevice device{};
+    pImpl->createDeviceImpl(device);
+    if (device.device == nil) {
+        return false;
+    }
+
+    MetalCommandQueue commandQueue{};
+    pImpl->createCommandQueueImpl(device, commandQueue);
+    if (commandQueue.commandQueue == nil) {
+        return false;
+    }
+
+    return true;
+}
+
 void PlatformMetal::createDevice(MetalDevice& outDevice) noexcept {
+    std::lock_guard<std::mutex> lock(pImpl->mLock);
+    pImpl->createDeviceImpl(outDevice);
+}
+
+void PlatformMetal::createCommandQueue(
+        MetalDevice& device, MetalCommandQueue& outCommandQueue) noexcept {
+    std::lock_guard<std::mutex> lock(pImpl->mLock);
+    pImpl->createCommandQueueImpl(device, outCommandQueue);
+}
+
+void PlatformMetal::createAndEnqueueCommandBuffer(MetalCommandBuffer& outCommandBuffer) noexcept {
+    std::lock_guard<std::mutex> lock(pImpl->mLock);
+    id<MTLCommandBuffer> commandBuffer = [pImpl->mCommandQueue commandBuffer];
+    [commandBuffer enqueue];
+    outCommandBuffer.commandBuffer = commandBuffer;
+}
+
+void PlatformMetal::setDrawableFailureBehavior(DrawableFailureBehavior behavior) noexcept {
+    pImpl->mDrawableFailureBehavior = behavior;
+}
+
+PlatformMetal::DrawableFailureBehavior PlatformMetal::getDrawableFailureBehavior() const noexcept {
+    return pImpl->mDrawableFailureBehavior;
+}
+
+// -------------------------------------------------------------------------------------------------
+
+void PlatformMetalImpl::createDeviceImpl(MetalDevice& outDevice) {
+    if (mDevice) {
+        outDevice.device = mDevice;
+        return;
+    }
+
     id<MTLDevice> result;
 
 #if !defined(FILAMENT_IOS)
@@ -74,27 +134,17 @@ void PlatformMetal::createDevice(MetalDevice& outDevice) noexcept {
                   << utils::io::endl;
 
     outDevice.device = result;
+    mDevice = result;
 }
 
-void PlatformMetal::createCommandQueue(
+void PlatformMetalImpl::createCommandQueueImpl(MetalDevice& device, MetalCommandQueue& outCommandQueue) {
-        MetalDevice& device, MetalCommandQueue& outCommandQueue) noexcept {
+    if (mCommandQueue) {
-    pImpl->mCommandQueue = [device.device newCommandQueue];
+        outCommandQueue.commandQueue = mCommandQueue;
-    pImpl->mCommandQueue.label = @"Filament";
+        return;
-    outCommandQueue.commandQueue = pImpl->mCommandQueue;
+    }
-}
+    mCommandQueue = [device.device newCommandQueue];
-
+    mCommandQueue.label = @"Filament";
-void PlatformMetal::createAndEnqueueCommandBuffer(MetalCommandBuffer& outCommandBuffer) noexcept {
+    outCommandQueue.commandQueue = mCommandQueue;
-    id<MTLCommandBuffer> commandBuffer = [pImpl->mCommandQueue commandBuffer];
-    [commandBuffer enqueue];
-    outCommandBuffer.commandBuffer = commandBuffer;
-}
-
-void PlatformMetal::setDrawableFailureBehavior(DrawableFailureBehavior behavior) noexcept {
-    pImpl->mDrawableFailureBehavior = behavior;
-}
-
-PlatformMetal::DrawableFailureBehavior PlatformMetal::getDrawableFailureBehavior() const noexcept {
-    return pImpl->mDrawableFailureBehavior;
 }
 
 } // namespace filament

filament/backend/src/opengl/BindingMap.h

@@ -69,9 +69,8 @@ public:
         assert_invariant(set < MAX_DESCRIPTOR_SET_COUNT);
         assert_invariant(binding < MAX_DESCRIPTOR_COUNT);
         assert_invariant(entry.binding < 128); // we reserve 1 bit for the type right now
-        mStorage[set][binding] = { (uint8_t)entry.binding,
+        mStorage[set][binding] = { uint8_t(entry.binding),
-                                   entry.type == DescriptorType::SAMPLER ||
+                                   DescriptorSetLayoutBinding::isSampler(entry.type) };
-                                   entry.type == DescriptorType::SAMPLER_EXTERNAL };
         mActiveDescriptors[set].set(binding);
     }
 

filament/backend/src/opengl/GLDescriptorSet.cpp

@@ -95,7 +95,32 @@ GLDescriptorSet::GLDescriptorSet(OpenGLContext& gl, DescriptorSetLayoutHandle ds
                 }
                 break;
             }
-            case DescriptorType::SAMPLER:
+
+            case DescriptorType::SAMPLER_2D_FLOAT:
+            case DescriptorType::SAMPLER_2D_INT:
+            case DescriptorType::SAMPLER_2D_UINT:
+            case DescriptorType::SAMPLER_2D_DEPTH:
+            case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_2D_ARRAY_INT:
+            case DescriptorType::SAMPLER_2D_ARRAY_UINT:
+            case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
+            case DescriptorType::SAMPLER_CUBE_FLOAT:
+            case DescriptorType::SAMPLER_CUBE_INT:
+            case DescriptorType::SAMPLER_CUBE_UINT:
+            case DescriptorType::SAMPLER_CUBE_DEPTH:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
+            case DescriptorType::SAMPLER_3D_FLOAT:
+            case DescriptorType::SAMPLER_3D_INT:
+            case DescriptorType::SAMPLER_3D_UINT:
+            case DescriptorType::SAMPLER_2D_MS_FLOAT:
+            case DescriptorType::SAMPLER_2D_MS_INT:
+            case DescriptorType::SAMPLER_2D_MS_UINT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
             case DescriptorType::SAMPLER_EXTERNAL:
                 if (UTILS_UNLIKELY(gl.isES2())) {
                     desc.emplace<SamplerGLES2>();

filament/backend/src/opengl/OpenGLBlobCache.cpp

@@ -21,7 +21,7 @@
 #include <backend/Platform.h>
 #include <backend/Program.h>
 
-#include <utils/Systrace.h>
+#include <private/utils/Tracing.h>
 
 namespace filament::backend {
 
@@ -36,7 +36,7 @@ OpenGLBlobCache::OpenGLBlobCache(OpenGLContext& gl) noexcept
 
 GLuint OpenGLBlobCache::retrieve(BlobCacheKey* outKey, Platform& platform,
         Program const& program) const noexcept {
-    SYSTRACE_CALL();
+    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
     if (!mCachingSupported || !platform.hasRetrieveBlobFunc()) {
         // the key is never updated in that case
         return 0;
@@ -68,7 +68,7 @@ GLuint OpenGLBlobCache::retrieve(BlobCacheKey* outKey, Platform& platform,
         programId = glCreateProgram();
 
         { // scope for systrace
-            SYSTRACE_NAME("glProgramBinary");
+            FILAMENT_TRACING_NAME(FILAMENT_TRACING_CATEGORY_FILAMENT, "glProgramBinary");
             glProgramBinary(programId, blob->format, blob->data, programBinarySize);
         }
 
@@ -90,7 +90,7 @@ GLuint OpenGLBlobCache::retrieve(BlobCacheKey* outKey, Platform& platform,
 
 void OpenGLBlobCache::insert(Platform& platform,
         BlobCacheKey const& key, GLuint program) noexcept {
-    SYSTRACE_CALL();
+    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
     if (!mCachingSupported || !platform.hasInsertBlobFunc()) {
         // the key is never updated in that case
         return;
@@ -100,7 +100,7 @@ void OpenGLBlobCache::insert(Platform& platform,
     GLenum format;
     GLint programBinarySize = 0;
     { // scope for systrace
-        SYSTRACE_NAME("glGetProgramiv");
+        FILAMENT_TRACING_NAME(FILAMENT_TRACING_CATEGORY_FILAMENT, "glGetProgramiv");
         glGetProgramiv(program, GL_PROGRAM_BINARY_LENGTH, &programBinarySize);
     }
     if (programBinarySize) {
@@ -108,7 +108,7 @@ void OpenGLBlobCache::insert(Platform& platform,
         std::unique_ptr<Blob, decltype(&::free)> blob{ (Blob*)malloc(size), &::free };
         if (UTILS_LIKELY(blob)) {
             { // scope for systrace
-                SYSTRACE_NAME("glGetProgramBinary");
+                FILAMENT_TRACING_NAME(FILAMENT_TRACING_CATEGORY_FILAMENT, "glGetProgramBinary");
                 glGetProgramBinary(program, programBinarySize,
                         &programBinarySize, &format, blob->data);
             }

filament/backend/src/opengl/OpenGLContext.cpp

@@ -542,6 +542,13 @@ void OpenGLContext::initBugs(Bugs* bugs, Extensions const& exts,
         } else if (strstr(renderer, "Intel")) {
             // Intel GPU
             bugs->vao_doesnt_store_element_array_buffer_binding = true;
+
+            if (strstr(renderer, "Mesa")) {
+                // Mesa Intel driver on Linux/Android
+                // Renderer of the form [Mesa Intel(R) HD Graphics 505 (APL 3)]
+                // b/405252622
+                bugs->disable_invalidate_framebuffer = true;
+            }
         } else if (strstr(renderer, "PowerVR")) {
             // PowerVR GPU
             // On PowerVR (Rogue GE8320) glFlush doesn't seem to do anything, in particular,

filament/backend/src/opengl/OpenGLDriver.cpp

@@ -44,6 +44,8 @@
 #include "private/backend/Dispatcher.h"
 #include "private/backend/DriverApi.h"
 
+#include <private/utils/Tracing.h>
+
 #include <type_traits>
 #include <utils/BitmaskEnum.h>
 #include <utils/FixedCapacityVector.h>
@@ -51,7 +53,6 @@
 #include <utils/Invocable.h>
 #include <utils/Log.h>
 #include <utils/Panic.h>
-#include <utils/Systrace.h>
 #include <utils/Slice.h>
 #include <utils/compiler.h>
 #include <utils/debug.h>
@@ -98,13 +99,13 @@
 
 #define DEBUG_GROUP_MARKER_NONE       0x00    // no debug marker
 #define DEBUG_GROUP_MARKER_OPENGL     0x01    // markers in the gl command queue (req. driver support)
-#define DEBUG_GROUP_MARKER_BACKEND    0x02    // markers on the backend side (systrace)
+#define DEBUG_GROUP_MARKER_BACKEND    0x02    // markers on the backend side (perfetto)
 #define DEBUG_GROUP_MARKER_ALL        0xFF    // all markers
 
 #define DEBUG_MARKER_NONE             0x00    // no debug marker
 #define DEBUG_MARKER_OPENGL           0x01    // markers in the gl command queue (req. driver support)
-#define DEBUG_MARKER_BACKEND          0x02    // markers on the backend side (systrace)
+#define DEBUG_MARKER_BACKEND          0x02    // markers on the backend side (perfetto)
-#define DEBUG_MARKER_PROFILE          0x04    // profiling on the backend side (systrace)
+#define DEBUG_MARKER_PROFILE          0x04    // profiling on the backend side (perfetto)
 #define DEBUG_MARKER_ALL              (0xFF & ~DEBUG_MARKER_PROFILE) // all markers
 
 // set to the desired debug marker level (for user markers [default: All])
@@ -248,8 +249,8 @@ OpenGLDriver::DebugMarker::DebugMarker(OpenGLDriver& driver, const char* string)
 #endif
 
 #if DEBUG_MARKER_LEVEL & DEBUG_MARKER_BACKEND
-    SYSTRACE_CONTEXT();
+    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    SYSTRACE_NAME_BEGIN(string);
+    FILAMENT_TRACING_NAME_BEGIN(FILAMENT_TRACING_CATEGORY_FILAMENT, string);
 #endif
 #endif
 }
@@ -265,8 +266,8 @@ OpenGLDriver::DebugMarker::~DebugMarker() noexcept {
 #endif
 
 #if DEBUG_MARKER_LEVEL & DEBUG_MARKER_BACKEND
-    SYSTRACE_CONTEXT();
+    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    SYSTRACE_NAME_END();
+    FILAMENT_TRACING_NAME_END(FILAMENT_TRACING_CATEGORY_FILAMENT);
 #endif
 #endif
 }
@@ -3348,8 +3349,8 @@ void OpenGLDriver::pushGroupMarker(char const* string) {
 #endif
 
 #if DEBUG_GROUP_MARKER_LEVEL & DEBUG_GROUP_MARKER_BACKEND
-    SYSTRACE_CONTEXT();
+    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    SYSTRACE_NAME_BEGIN(string);
+    FILAMENT_TRACING_NAME_BEGIN(FILAMENT_TRACING_CATEGORY_FILAMENT, string);
 #endif
 #endif
 }
@@ -3365,8 +3366,8 @@ void OpenGLDriver::popGroupMarker(int) {
 #endif
 
 #if DEBUG_GROUP_MARKER_LEVEL & DEBUG_GROUP_MARKER_BACKEND
-    SYSTRACE_CONTEXT();
+    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    SYSTRACE_NAME_END();
+    FILAMENT_TRACING_NAME_END(FILAMENT_TRACING_CATEGORY_FILAMENT);
 #endif
 #endif
 }
@@ -3685,7 +3686,7 @@ void OpenGLDriver::endFrame(UTILS_UNUSED uint32_t frameId) {
     gl.depthFunc(GL_LESS);
     gl.disable(GL_SCISSOR_TEST);
 #endif
-    //SYSTRACE_NAME("glFinish");
+    //FILAMENT_TRACING_NAME(FILAMENT_TRACING_CATEGORY_FILAMENT, "glFinish");
     //glFinish();
     mPlatform.endFrame(frameId);
     insertEventMarker("endFrame");

filament/backend/src/opengl/OpenGLProgram.cpp

@@ -25,12 +25,13 @@
 #include <backend/Program.h>
 #include <backend/Handle.h>
 
+#include <private/utils/Tracing.h>
+
 #include <utils/BitmaskEnum.h>
 #include <utils/compiler.h>
 #include <utils/debug.h>
 #include <utils/FixedCapacityVector.h>
 #include <utils/Log.h>
-#include <utils/Systrace.h>
 
 #include <algorithm>
 #include <array>
@@ -96,8 +97,7 @@ OpenGLProgram::~OpenGLProgram() noexcept {
 }
 
 void OpenGLProgram::initialize(OpenGLDriver& gld) {
-
+    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    SYSTRACE_CALL();
 
     assert_invariant(gl.program == 0);
     assert_invariant(mToken);
@@ -122,8 +122,7 @@ void OpenGLProgram::initialize(OpenGLDriver& gld) {
  */
 void OpenGLProgram::initializeProgramState(OpenGLContext& context, GLuint program,
         LazyInitializationData& lazyInitializationData) noexcept {
-
+    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    SYSTRACE_CALL();
 
     // from the pipeline layout we compute a mapping from {set, binding} to {binding}
     // for both buffers and textures
@@ -175,7 +174,31 @@ void OpenGLProgram::initializeProgramState(OpenGLContext& context, GLuint progra
                     }
                     break;
                 }
-                case DescriptorType::SAMPLER:
+                case DescriptorType::SAMPLER_2D_FLOAT:
+                case DescriptorType::SAMPLER_2D_INT:
+                case DescriptorType::SAMPLER_2D_UINT:
+                case DescriptorType::SAMPLER_2D_DEPTH:
+                case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
+                case DescriptorType::SAMPLER_2D_ARRAY_INT:
+                case DescriptorType::SAMPLER_2D_ARRAY_UINT:
+                case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
+                case DescriptorType::SAMPLER_CUBE_FLOAT:
+                case DescriptorType::SAMPLER_CUBE_INT:
+                case DescriptorType::SAMPLER_CUBE_UINT:
+                case DescriptorType::SAMPLER_CUBE_DEPTH:
+                case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
+                case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
+                case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
+                case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
+                case DescriptorType::SAMPLER_3D_FLOAT:
+                case DescriptorType::SAMPLER_3D_INT:
+                case DescriptorType::SAMPLER_3D_UINT:
+                case DescriptorType::SAMPLER_2D_MS_FLOAT:
+                case DescriptorType::SAMPLER_2D_MS_INT:
+                case DescriptorType::SAMPLER_2D_MS_UINT:
+                case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
+                case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
+                case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
                 case DescriptorType::SAMPLER_EXTERNAL: {
                     if (!entry.name.empty()) {
                         GLint const loc = glGetUniformLocation(program, entry.name.c_str());

filament/backend/src/opengl/OpenGLTimerQuery.cpp

@@ -23,12 +23,13 @@
 #include <backend/platforms/OpenGLPlatform.h>
 #include <backend/DriverEnums.h>
 
+#include <private/utils/Tracing.h>
+
 #include <utils/compiler.h>
 #include <utils/debug.h>
 #include <utils/JobSystem.h>
 #include <utils/Log.h>
 #include <utils/Mutex.h>
-#include <utils/Systrace.h>
 
 #include <atomic>
 #include <memory>
@@ -240,8 +241,8 @@ void TimerQueryFenceFactory::beginTimeElapsedQuery(GLTimerQuery* tq) {
         if (state) {
             platform.waitFence(fence, FENCE_WAIT_FOR_EVER);
             state->then = clock::now().time_since_epoch().count();
-            SYSTRACE_CONTEXT();
+            FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-            SYSTRACE_ASYNC_BEGIN("OpenGLTimerQueryFence", intptr_t(state.get()));
+            FILAMENT_TRACING_ASYNC_BEGIN(FILAMENT_TRACING_CATEGORY_FILAMENT, "OpenGLTimerQueryFence", intptr_t(state.get()));
         }
         platform.destroyFence(fence);
     });
@@ -257,8 +258,8 @@ void TimerQueryFenceFactory::endTimeElapsedQuery(OpenGLDriver&, GLTimerQuery* tq
             platform.waitFence(fence, FENCE_WAIT_FOR_EVER);
             int64_t const now = clock::now().time_since_epoch().count();
             state->elapsed.store(now - state->then, std::memory_order_relaxed);
-            SYSTRACE_CONTEXT();
+            FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-            SYSTRACE_ASYNC_END("OpenGLTimerQueryFence", intptr_t(state.get()));
+            FILAMENT_TRACING_ASYNC_END(FILAMENT_TRACING_CATEGORY_FILAMENT, "OpenGLTimerQueryFence", intptr_t(state.get()));
         }
         platform.destroyFence(fence);
     });

filament/backend/src/opengl/ShaderCompilerService.cpp

@@ -28,6 +28,8 @@
 #include <backend/DriverEnums.h>
 #include <backend/Program.h>
 
+#include <private/utils/Tracing.h>
+
 #include <utils/compiler.h>
 #include <utils/CString.h>
 #include <utils/debug.h>
@@ -36,7 +38,6 @@
 #include <utils/Log.h>
 #include <utils/ostream.h>
 #include <utils/Panic.h>
-#include <utils/Systrace.h>
 
 #include <algorithm>
 #include <array>
@@ -367,7 +368,7 @@ void ShaderCompilerService::notifyWhenAllProgramsAreReady(
 
 GLuint ShaderCompilerService::initialize(program_token_t& token) {
 
-    SYSTRACE_CALL();
+    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
 
     assert_invariant(token);// This function should be called when the token is still alive.
 
@@ -454,8 +455,8 @@ void ShaderCompilerService::runAtNextTick(CompilerPriorityQueue priority,
             });
     ops.emplace(pos, priority, token, std::move(job));
 
-    SYSTRACE_CONTEXT();
+    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    SYSTRACE_VALUE32("ShaderCompilerService Jobs", mRunAtNextTickOps.size());
+    FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "ShaderCompilerService Jobs", mRunAtNextTickOps.size());
 }
 
 bool ShaderCompilerService::cancelTickOp(program_token_t const& token) noexcept {
@@ -468,8 +469,8 @@ bool ShaderCompilerService::cancelTickOp(program_token_t const& token) noexcept
         ops.erase(pos);
         return true;
     }
-    SYSTRACE_CONTEXT();
+    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    SYSTRACE_VALUE32("ShaderCompilerService Jobs", ops.size());
+    FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "ShaderCompilerService Jobs", ops.size());
     return false;
 }
 
@@ -485,15 +486,15 @@ void ShaderCompilerService::executeTickOps() noexcept {
             ++it;
         }
     }
-    SYSTRACE_CONTEXT();
+    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    SYSTRACE_VALUE32("ShaderCompilerService Jobs", ops.size());
+    FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "ShaderCompilerService Jobs", ops.size());
 }
 
 /* static */ void ShaderCompilerService::compileShaders(OpenGLContext& context,
         Program::ShaderSource shadersSource,
         FixedCapacityVector<Program::SpecializationConstant> const& specializationConstants,
         bool multiview, program_token_t const& token) noexcept {
-    SYSTRACE_CALL();
+    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
 
     auto const appendSpecConstantString = +[](std::string& s, Program::SpecializationConstant const& sc) {
         s += "#define SPIRV_CROSS_CONSTANT_ID_" + std::to_string(sc.id) + ' ';
@@ -616,7 +617,7 @@ void ShaderCompilerService::executeTickOps() noexcept {
 }
 
 /* static */ void ShaderCompilerService::checkCompileStatus(program_token_t const& token) noexcept {
-    SYSTRACE_CALL();
+    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
 
     UTILS_NOUNROLL
     for (size_t i = 0; i < Program::SHADER_TYPE_COUNT; i++) {
@@ -639,7 +640,7 @@ void ShaderCompilerService::executeTickOps() noexcept {
 
 /* static */ void ShaderCompilerService::linkProgram(OpenGLContext const& context,
         program_token_t const& token) noexcept {
-    SYSTRACE_CALL();
+    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
 
     // Shader compilation should be completed by now. Check the status and log errors on failure.
     checkCompileStatus(token);
@@ -675,7 +676,7 @@ void ShaderCompilerService::executeTickOps() noexcept {
 
 /* static */ bool ShaderCompilerService::checkLinkStatusAndCleanupShaders(
         program_token_t const& token) noexcept {
-    SYSTRACE_CALL();
+    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
     assert_invariant(token->gl.program);
 
     bool linked = true;

filament/backend/src/opengl/platforms/PlatformCocoaGL.mm

@@ -54,7 +54,7 @@ struct PlatformCocoaGLImpl {
     CVOpenGLTextureCacheRef mTextureCache = nullptr;
     std::unique_ptr<CocoaExternalImage::SharedGl> mExternalImageSharedGl;
     void updateOpenGLContext(NSView *nsView, bool resetView, bool clearView);
-    struct ExternalImageCocoaGL : public Platform::ExternalImage {
+    struct ExternalImageCocoaGL final : public Platform::ExternalImage {
         CVPixelBufferRef cvBuffer;
     protected:
         ~ExternalImageCocoaGL() noexcept final;

filament/backend/src/opengl/platforms/PlatformEGLAndroid.cpp

@@ -255,6 +255,7 @@ Platform::ExternalImageHandle PlatformEGLAndroid::createExternalImage(AHardwareB
         p->height = hardwareBufferDescription.height;
         p->width = hardwareBufferDescription.width;
         auto textureFormat = mapToFilamentFormat(hardwareBufferDescription.format, sRGB);
+        p->format = textureFormat;
         p->usage = mapToFilamentUsage(hardwareBufferDescription.usage, textureFormat);
         return ExternalImageHandle{ p };
     }

filament/backend/src/vulkan/VulkanBuffer.cpp

@@ -28,7 +28,7 @@ VulkanBuffer::VulkanBuffer(VmaAllocator allocator, VulkanStagePool& stagePool,
     : mAllocator(allocator),
       mStagePool(stagePool),
       mUsage(usage),
-	  mUpdatedOffset(0),
+      mUpdatedOffset(0),
       mUpdatedBytes(0) {
     // for now make sure that only 1 bit is set in usage
     // (because loadFromCpu() assumes that somewhat)
@@ -56,11 +56,12 @@ void VulkanBuffer::loadFromCpu(VkCommandBuffer cmdbuf, const void* cpuData, uint
     vmaMapMemory(mAllocator, stage->memory, &mapped);
     memcpy(mapped, cpuData, numBytes);
     vmaUnmapMemory(mAllocator, stage->memory);
-    vmaFlushAllocation(mAllocator, stage->memory, byteOffset, numBytes);
+    vmaFlushAllocation(mAllocator, stage->memory, 0, numBytes);
 
     // If there was a previous update, then we need to make sure the following write is properly
     // synced with the previous read.
-    if (mUpdatedBytes > 0) {
+    if (mUpdatedBytes > 0 &&
+            (byteOffset >= mUpdatedOffset && byteOffset <= (mUpdatedOffset + mUpdatedBytes))) {
         VkAccessFlags srcAccess = 0;
         VkPipelineStageFlags srcStage = 0;
         if (mUsage & VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT) {
@@ -74,28 +75,28 @@ void VulkanBuffer::loadFromCpu(VkCommandBuffer cmdbuf, const void* cpuData, uint
             srcStage = VK_PIPELINE_STAGE_VERTEX_INPUT_BIT;
         }
 
-        VkBufferMemoryBarrier barrier{
+        VkBufferMemoryBarrier barrier = {
             .sType = VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER,
             .srcAccessMask = srcAccess,
             .dstAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT,
             .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
             .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
             .buffer = mGpuBuffer,
-			.offset = mUpdatedOffset,
+            .offset = byteOffset,
-            .size = mUpdatedBytes,
+            .size = numBytes,
         };
         vkCmdPipelineBarrier(cmdbuf, srcStage, VK_PIPELINE_STAGE_TRANSFER_BIT, 0, 0, nullptr, 1,
                 &barrier, 0, nullptr);
     }
 
-    VkBufferCopy region {
+    VkBufferCopy region = {
-            .srcOffset = 0,
+        .srcOffset = 0,
-            .dstOffset = byteOffset,
+        .dstOffset = byteOffset,
-            .size = numBytes,
+        .size = numBytes,
     };
     vkCmdCopyBuffer(cmdbuf, stage->buffer, mGpuBuffer, 1, &region);
 
-	mUpdatedOffset = byteOffset;
+    mUpdatedOffset = byteOffset;
     mUpdatedBytes = numBytes;
 
     // Firstly, ensure that the copy finishes before the next draw call.
@@ -112,21 +113,21 @@ void VulkanBuffer::loadFromCpu(VkCommandBuffer cmdbuf, const void* cpuData, uint
         dstAccessMask |= VK_ACCESS_INDEX_READ_BIT;
         dstStageMask |= VK_PIPELINE_STAGE_VERTEX_INPUT_BIT;
     } else if (mUsage & VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT) {
-        dstAccessMask |= VK_ACCESS_UNIFORM_READ_BIT;
+        dstAccessMask |= VK_ACCESS_SHADER_READ_BIT;
-        dstStageMask |=
+        dstStageMask |= VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT | VK_PIPELINE_STAGE_VERTEX_SHADER_BIT;
-                (VK_PIPELINE_STAGE_VERTEX_SHADER_BIT | VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT);
     } else if (mUsage & VK_BUFFER_USAGE_STORAGE_BUFFER_BIT) {
         // TODO: implement me
     }
 
-    VkBufferMemoryBarrier barrier{
+    VkBufferMemoryBarrier barrier = {
         .sType = VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER,
         .srcAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT,
         .dstAccessMask = dstAccessMask,
         .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
         .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
         .buffer = mGpuBuffer,
-        .size = VK_WHOLE_SIZE,
+        .offset = byteOffset,
+        .size = numBytes,
     };
 
     vkCmdPipelineBarrier(cmdbuf, VK_PIPELINE_STAGE_TRANSFER_BIT, dstStageMask, 0, 0, nullptr, 1,

filament/backend/src/vulkan/VulkanConstants.h

@@ -151,13 +151,13 @@ static_assert(FVK_ENABLED(FVK_DEBUG_VALIDATION));
 
 #elif FVK_ENABLED(FVK_DEBUG_SYSTRACE)
 
-    #include <utils/Systrace.h>
+    #include <private/utils/Tracing.h>
 
-    #define FVK_SYSTRACE_CONTEXT()      SYSTRACE_CONTEXT()
+    #define FVK_SYSTRACE_CONTEXT()      FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT)
-    #define FVK_SYSTRACE_START(marker)  SYSTRACE_NAME_BEGIN(marker)
+    #define FVK_SYSTRACE_START(marker)  FILAMENT_TRACING_NAME_BEGIN(FILAMENT_TRACING_CATEGORY_FILAMENT, marker)
-    #define FVK_SYSTRACE_END()          SYSTRACE_NAME_END()
+    #define FVK_SYSTRACE_END()          FILAMENT_TRACING_NAME_END(FILAMENT_TRACING_CATEGORY_FILAMENT)
-    #define FVK_SYSTRACE_SCOPE()        SYSTRACE_CALL()
+    #define FVK_SYSTRACE_SCOPE()        FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT)
-    #define FVK_PROFILE_MARKER(marker)  SYSTRACE_CALL()
+    #define FVK_PROFILE_MARKER(marker)  FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT)
 
 #else
     #define FVK_SYSTRACE_CONTEXT()

filament/backend/src/vulkan/VulkanContext.h

@@ -142,6 +142,10 @@ public:
         return mPortabilitySubsetFeatures.imageView2DOn3DImage == VK_TRUE;
     }
 
+    inline bool isUnifiedMemoryArchitecture() const noexcept {
+        return mIsUnifiedMemoryArchitecture;
+    }
+
 private:
     VkPhysicalDeviceMemoryProperties mMemoryProperties = {};
     VkPhysicalDeviceProperties2 mPhysicalDeviceProperties = {
@@ -164,6 +168,7 @@ private:
     bool mDebugUtilsSupported = false;
     bool mLazilyAllocatedMemorySupported = false;
     bool mProtectedMemorySupported = false;
+    bool mIsUnifiedMemoryArchitecture = false;
 
     fvkutils::VkFormatList mDepthStencilFormats;
     fvkutils::VkFormatList mBlittableDepthStencilFormats;

filament/backend/src/vulkan/VulkanDescriptorSetCache.cpp

@@ -358,12 +358,11 @@ void VulkanDescriptorSetCache::updateSamplerImpl(VkDescriptorSet vkset, uint8_t
         range.levelCount = 1;
         range.layerCount = 1;
     }
-    VkDescriptorImageInfo info{
+    VkDescriptorImageInfo info = {
         .sampler = sampler,
         .imageView = texture->getView(range),
-        .imageLayout = fvkutils::getVkLayout(texture->getDefaultLayout()),
+        .imageLayout = fvkutils::getVkLayout(texture->getSamplerLayout()),
     };
-
     VkWriteDescriptorSet descriptorWrite = {
         .sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET,
         .pNext = nullptr,

filament/backend/src/vulkan/VulkanDriver.cpp

@@ -622,7 +622,7 @@ void VulkanDriver::createTextureExternalImage2R(Handle<HwTexture> th, backend::S
     auto& commands = mCommands.get();
     // Unlike uploaded textures or swapchains, we need to explicit transition this
     // texture into the read layout.
-    texture->transitionLayout(&commands, texture->getPrimaryViewRange(), VulkanLayout::READ_ONLY);
+    texture->transitionLayout(&commands, texture->getPrimaryViewRange(), VulkanLayout::FRAG_READ);
 
     if (imgData.external.valid()) {
         mExternalImageManager.addExternallySampledTexture(texture, externalImage);

filament/backend/src/vulkan/VulkanHandles.cpp

@@ -93,7 +93,32 @@ BitmaskGroup fromBackendLayout(DescriptorSetLayout const& layout) {
             case DescriptorType::SAMPLER_EXTERNAL:
                 fromStageFlags(binding.stageFlags, binding.binding, mask.externalSampler);
                 UTILS_FALLTHROUGH;
-            case DescriptorType::SAMPLER: {
+
+            case DescriptorType::SAMPLER_2D_FLOAT:
+            case DescriptorType::SAMPLER_2D_INT:
+            case DescriptorType::SAMPLER_2D_UINT:
+            case DescriptorType::SAMPLER_2D_DEPTH:
+            case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_2D_ARRAY_INT:
+            case DescriptorType::SAMPLER_2D_ARRAY_UINT:
+            case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
+            case DescriptorType::SAMPLER_CUBE_FLOAT:
+            case DescriptorType::SAMPLER_CUBE_INT:
+            case DescriptorType::SAMPLER_CUBE_UINT:
+            case DescriptorType::SAMPLER_CUBE_DEPTH:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
+            case DescriptorType::SAMPLER_3D_FLOAT:
+            case DescriptorType::SAMPLER_3D_INT:
+            case DescriptorType::SAMPLER_3D_UINT:
+            case DescriptorType::SAMPLER_2D_MS_FLOAT:
+            case DescriptorType::SAMPLER_2D_MS_INT:
+            case DescriptorType::SAMPLER_2D_MS_UINT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT: {
                 fromStageFlags(binding.stageFlags, binding.binding, mask.sampler);
                 break;
             }
@@ -495,7 +520,8 @@ void VulkanRenderTarget::emitBarriersEndRenderPass(VulkanCommandBuffer& commands
             }
         } else {
             texture->setLayout(range, VulkanFboCache::FINAL_COLOR_ATTACHMENT_LAYOUT);
-            if (!texture->transitionLayout(&commands, range, VulkanLayout::READ_WRITE)) {
+            if (texture->isSampleable() &&
+                    !texture->transitionLayout(&commands, range, VulkanLayout::FRAG_READ)) {
                 texture->attachmentToSamplerBarrier(&commands, range);
             }
         }

filament/backend/src/vulkan/VulkanReadPixels.cpp

@@ -234,6 +234,7 @@ void VulkanReadPixels::run(fvkmemory::resource_ptr<VulkanRenderTarget> srcTarget
 
     VulkanAttachment const srcAttachment = srcTarget->getColor0();
     VkImageSubresourceRange const srcRange = srcAttachment.getSubresourceRange();
+    VulkanLayout const srcLayout = srcAttachment.getLayout();
     srcTexture->transitionLayout(cmdbuffer, srcRange, VulkanLayout::TRANSFER_SRC);
 
     VkImageCopy const imageCopyRegion = {
@@ -270,7 +271,7 @@ void VulkanReadPixels::run(fvkmemory::resource_ptr<VulkanRenderTarget> srcTarget
             fvkutils::getVkLayout(VulkanLayout::TRANSFER_DST), 1, &imageCopyRegion);
 
     // Restore the source image layout.
-    srcTexture->transitionLayout(cmdbuffer, srcRange, srcTexture->getDefaultLayout());
+    srcTexture->transitionLayout(cmdbuffer, srcRange, srcLayout);
 
     vkEndCommandBuffer(cmdbuffer);
 

filament/backend/src/vulkan/VulkanStagePool.cpp

@@ -125,7 +125,7 @@ VulkanStageImage const* VulkanStagePool::acquireImage(PixelDataFormat format, Pi
     fvkutils::transitionLayout(cmdbuffer, {
             .image = image->image,
             .oldLayout = VulkanLayout::UNDEFINED,
-            .newLayout = VulkanLayout::READ_WRITE, // (= VK_IMAGE_LAYOUT_GENERAL)
+            .newLayout = VulkanLayout::STAGING, // (= VK_IMAGE_LAYOUT_GENERAL)
             .subresources = { aspectFlags, 0, 1, 0, 1 },
         });
     return image;

filament/backend/src/vulkan/VulkanTexture.cpp

@@ -125,7 +125,7 @@ inline VulkanLayout getDefaultLayoutImpl(TextureUsage usage) {
         return VulkanLayout::COLOR_ATTACHMENT;
     }
     // Finally, the layout for an immutable texture is optimal read-only.
-    return VulkanLayout::READ_ONLY;
+    return VulkanLayout::FRAG_READ;
 }
 
 inline VulkanLayout getDefaultLayoutImpl(VkImageUsageFlags vkusage) {
@@ -187,7 +187,7 @@ VkImageUsageFlags getUsage(VulkanContext const& context, uint8_t samples,
             VkFormatProperties props;
             vkGetPhysicalDeviceFormatProperties(physicalDevice, vkFormat, &props);
             if (!(props.optimalTilingFeatures & VK_FORMAT_FEATURE_SAMPLED_IMAGE_BIT)) {
-                FVK_LOGW << "Texture usage is SAMPLEABLE but format " << mState->mVkFormat << " is not "
+                FVK_LOGW << "Texture usage is SAMPLEABLE but format " << vkFormat << " is not "
                         "sampleable with optimal tiling." << utils::io::endl;
             }
         }
@@ -691,6 +691,7 @@ bool VulkanTexture::transitionLayout(VkCommandBuffer cmdbuf, VkImageSubresourceR
                  << " is skipped because of no change in layout" << utils::io::endl;
 #endif
     }
+
     return hasTransitions;
 }
 
@@ -700,16 +701,15 @@ void VulkanTexture::samplerToAttachmentBarrier(VulkanCommandBuffer* commands,
     VkImageLayout const layout =
             fvkutils::getVkLayout(getLayout(range.baseArrayLayer, range.baseMipLevel));
     VkImageMemoryBarrier barrier = {
-            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+        .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
-            .srcAccessMask = VK_ACCESS_SHADER_READ_BIT,
+        .srcAccessMask = VK_ACCESS_SHADER_READ_BIT,
-            .dstAccessMask =
+        .dstAccessMask = VK_ACCESS_COLOR_ATTACHMENT_READ_BIT | VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
-                    VK_ACCESS_COLOR_ATTACHMENT_READ_BIT | VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
+        .oldLayout = layout,
-            .oldLayout = layout,
+        .newLayout = layout,
-            .newLayout = layout,
+        .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
-            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+        .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
-            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+        .image = mState->mTextureImage,
-            .image = mState->mTextureImage,
+        .subresourceRange = range,
-            .subresourceRange = range,
     };
     vkCmdPipelineBarrier(cmdbuf, VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT,
             VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT |
@@ -723,15 +723,15 @@ void VulkanTexture::attachmentToSamplerBarrier(VulkanCommandBuffer* commands,
     VkImageLayout const layout
             = fvkutils::getVkLayout(getLayout(range.baseArrayLayer, range.baseMipLevel));
     VkImageMemoryBarrier barrier = {
-            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+        .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
-            .srcAccessMask = VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
+        .srcAccessMask = VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
-            .dstAccessMask = VK_ACCESS_SHADER_READ_BIT,
+        .dstAccessMask = VK_ACCESS_SHADER_READ_BIT,
-            .oldLayout = layout,
+        .oldLayout = layout,
-            .newLayout = layout,
+        .newLayout = layout,
-            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+        .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
-            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+        .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
-            .image = mState->mTextureImage,
+        .image = mState->mTextureImage,
-            .subresourceRange = range,
+        .subresourceRange = range,
     };
     vkCmdPipelineBarrier(cmdbuf, VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT,
             VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT, 0, 0, nullptr, 0, nullptr, 1, &barrier);

filament/backend/src/vulkan/VulkanTexture.h

@@ -145,8 +145,14 @@ struct VulkanTexture : public HwTexture, fvkmemory::Resource {
 
     VkImageSubresourceRange const& getPrimaryViewRange() const { return mPrimaryViewRange; }
 
-    VulkanLayout getPrimaryImageLayout() const {
+    VulkanLayout getSamplerLayout() const {
-        return getLayout(mPrimaryViewRange.baseArrayLayer, mPrimaryViewRange.baseMipLevel);
+        if (!isSampleable()) {
+            return VulkanLayout::UNDEFINED;
+        }
+        if (mState->mUsage & VK_IMAGE_USAGE_DEPTH_STENCIL_ATTACHMENT_BIT) {
+            return VulkanLayout::DEPTH_SAMPLER;
+        }
+        return VulkanLayout::FRAG_READ;
     }
 
     // Returns the layout for the intended use of this texture (and not the expected layout at the
@@ -180,6 +186,10 @@ struct VulkanTexture : public HwTexture, fvkmemory::Resource {
         return mState->mUsage & VK_IMAGE_USAGE_TRANSIENT_ATTACHMENT_BIT;
     }
 
+    bool isSampleable() const {
+        return mState->mUsage & VK_IMAGE_USAGE_SAMPLED_BIT;
+    }
+
     bool getIsProtected() const {
         return mState->mIsProtected;
     }

filament/backend/src/vulkan/platform/VulkanPlatform.cpp

@@ -631,6 +631,21 @@ fvkutils::VkFormatList findBlittableDepthStencilFormats(VkPhysicalDevice device)
     return ret;
 }
 
+/**
+ *  Check if the GPU has a unified memory architecture.
+ */
+bool hasUnifiedMemoryArchitecture(VkPhysicalDeviceMemoryProperties memoryProperties) noexcept {
+    // Try to identify if the platform is running on a Unified Memory Architecture by inspecting the
+    // memory heap flags, if they are all VK_MEMORY_HEAP_DEVICE_LOCAL_BIT it's UMA, otherwise not
+    // enough information to make a decision, so default to false.
+    for (uint32_t i = 0; i < memoryProperties.memoryHeapCount; ++i) {
+        if ((memoryProperties.memoryHeaps[i].flags & VK_MEMORY_HEAP_DEVICE_LOCAL_BIT) == 0) {
+            return false;
+        }
+    }
+    return true;
+}
+
 }// anonymous namespace
 
 using SwapChainPtr = VulkanPlatform::SwapChainPtr;
@@ -864,6 +879,8 @@ Driver* VulkanPlatform::createDriver(void* sharedContext,
         }
     }
 
+    context.mIsUnifiedMemoryArchitecture = hasUnifiedMemoryArchitecture(context.mMemoryProperties);
+
 #ifdef NDEBUG
     // If we are in release build, we should not have turned on debug extensions
     FILAMENT_CHECK_POSTCONDITION(!context.mDebugUtilsSupported && !context.mDebugMarkersSupported)

filament/backend/src/vulkan/utils/Image.cpp

@@ -42,20 +42,22 @@ getVkTransition(const VulkanLayoutTransition& transition) {
             srcStage = VK_PIPELINE_STAGE_ALL_GRAPHICS_BIT;
             break;
         case VulkanLayout::COLOR_ATTACHMENT:
-            srcAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT |
+            srcAccessMask = VK_ACCESS_COLOR_ATTACHMENT_READ_BIT |
-                            VK_ACCESS_COLOR_ATTACHMENT_READ_BIT |
                             VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT;
-            srcStage = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT | VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT |
+            srcStage = VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT;
-                       VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT;
             break;
-        case VulkanLayout::READ_WRITE:
+        case VulkanLayout::STAGING:
             srcAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT;
             srcStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
             break;
-        case VulkanLayout::READ_ONLY:
+        case VulkanLayout::FRAG_READ:
             srcAccessMask = VK_ACCESS_SHADER_READ_BIT;
             srcStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
             break;
+        case VulkanLayout::VERT_READ:
+            srcAccessMask = VK_ACCESS_SHADER_READ_BIT;
+            srcStage = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT;
+            break;
         case VulkanLayout::TRANSFER_SRC:
             srcAccessMask = VK_ACCESS_TRANSFER_READ_BIT;
             srcStage = VK_PIPELINE_STAGE_TRANSFER_BIT;
@@ -69,7 +71,7 @@ getVkTransition(const VulkanLayoutTransition& transition) {
             srcStage = VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT;
             break;
         case VulkanLayout::DEPTH_SAMPLER:
-            srcAccessMask = VK_ACCESS_MEMORY_READ_BIT;
+            srcAccessMask = VK_ACCESS_SHADER_READ_BIT;
             srcStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
             break;
         case VulkanLayout::COLOR_ATTACHMENT_RESOLVE:
@@ -84,19 +86,21 @@ getVkTransition(const VulkanLayoutTransition& transition) {
 
     switch (transition.newLayout) {
         case VulkanLayout::COLOR_ATTACHMENT:
-            dstAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT
+            dstAccessMask = VK_ACCESS_COLOR_ATTACHMENT_READ_BIT
-                            | VK_ACCESS_COLOR_ATTACHMENT_READ_BIT
                             | VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT;
-            dstStage = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT | VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT
+            dstStage = VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT | VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
-                       | VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT;
             break;
-        case VulkanLayout::READ_WRITE:
+        case VulkanLayout::STAGING:
             dstAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT;
             dstStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
             break;
-        case VulkanLayout::READ_ONLY:
+        case VulkanLayout::FRAG_READ:
             dstAccessMask = VK_ACCESS_SHADER_READ_BIT;
-            dstStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT | VK_PIPELINE_STAGE_VERTEX_SHADER_BIT;
+            dstStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
+            break;
+        case VulkanLayout::VERT_READ:
+            dstAccessMask = VK_ACCESS_SHADER_READ_BIT;
+            dstStage = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT;
             break;
         case VulkanLayout::TRANSFER_SRC:
             dstAccessMask = VK_ACCESS_TRANSFER_READ_BIT;
@@ -112,10 +116,8 @@ getVkTransition(const VulkanLayoutTransition& transition) {
             dstStage = VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT;
             break;
         case VulkanLayout::DEPTH_SAMPLER:
-            dstAccessMask =
+            dstAccessMask = VK_ACCESS_SHADER_READ_BIT;
-                    VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT;
+            dstStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
-            dstStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT |
-                       VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT;
             break;
         case VulkanLayout::PRESENT:
         case VulkanLayout::COLOR_ATTACHMENT_RESOLVE:
@@ -138,7 +140,6 @@ bool transitionLayout(VkCommandBuffer cmdbuffer,
     }
     auto [srcAccessMask, dstAccessMask, srcStage, dstStage, oldLayout, newLayout]
             = getVkTransition(transition);
-
     if (oldLayout == newLayout) {
         return false;
     }
@@ -155,7 +156,7 @@ bool transitionLayout(VkCommandBuffer cmdbuffer,
             .image = transition.image,
             .subresourceRange = transition.subresources,
     };
-    vkCmdPipelineBarrier(cmdbuffer, srcStage, dstStage, 0, 0, nullptr, 0, nullptr, 1, &barrier);
+   vkCmdPipelineBarrier(cmdbuffer, srcStage, dstStage, 0, 0, nullptr, 0, nullptr, 1, &barrier);
     return true;
 }
 
@@ -264,8 +265,9 @@ utils::io::ostream& operator<<(utils::io::ostream& out,
         const filament::backend::VulkanLayout& layout) {
     switch (layout) {
         CASE(UNDEFINED)
-        CASE(READ_ONLY)
+        CASE(FRAG_READ)
-        CASE(READ_WRITE)
+        CASE(VERT_READ)
+        CASE(STAGING)
         CASE(TRANSFER_SRC)
         CASE(TRANSFER_DST)
         CASE(DEPTH_ATTACHMENT)

filament/backend/src/vulkan/utils/Image.h

@@ -32,9 +32,11 @@ enum class VulkanLayout : uint8_t {
     // any transition.
     UNDEFINED,
     // Fragment/vertex shader accessible layout for reading and writing.
-    READ_WRITE,
+    STAGING,
-    // Fragment/vertex shader accessible layout for reading only.
+    // Fragment shader accessible layout for reading only.
-    READ_ONLY,
+    FRAG_READ,
+    // Vertex shader accessible layout for reading only.
+    VERT_READ,
     // For the source of a copy operation.
     TRANSFER_SRC,
     // For the destination of a copy operation.
@@ -65,9 +67,10 @@ constexpr inline VkImageLayout getVkLayout(VulkanLayout layout) {
     switch (layout) {
         case VulkanLayout::UNDEFINED:
             return VK_IMAGE_LAYOUT_UNDEFINED;
-        case VulkanLayout::READ_WRITE:
+        case VulkanLayout::STAGING:
             return VK_IMAGE_LAYOUT_GENERAL;
-        case VulkanLayout::READ_ONLY:
+        case VulkanLayout::FRAG_READ:
+        case VulkanLayout::VERT_READ:
             return VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL;
         case VulkanLayout::TRANSFER_SRC:
             return VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL;
@@ -80,9 +83,8 @@ constexpr inline VkImageLayout getVkLayout(VulkanLayout layout) {
         case VulkanLayout::PRESENT:
             return VK_IMAGE_LAYOUT_PRESENT_SRC_KHR;
         // Filament sometimes samples from one miplevel while writing to another level in the
-        // same texture (e.g. bloom does this). Moreover we'd like to avoid lots of expensive
+        // same texture (e.g. bloom does this). So, keep it simple and use GENERAL for all
-        // layout transitions. So, keep it simple and use GENERAL for all color-attachable
+        // color-attachable textures.
-        // textures.
         case VulkanLayout::COLOR_ATTACHMENT:
             return VK_IMAGE_LAYOUT_GENERAL;
         case VulkanLayout::COLOR_ATTACHMENT_RESOLVE:

filament/backend/src/webgpu/WebGPUDriver.cpp

@@ -13,7 +13,7 @@
  * See the License for the specific language governing permissions and
  * limitations under the License.
  */
-
+#include <utils/Hash.h>
 #include "webgpu/WebGPUDriver.h"
 
 #include "WebGPUPipelineCreation.h"
@@ -26,7 +26,7 @@
 #include <backend/DriverEnums.h>
 #include <backend/Handle.h>
 #include <backend/TargetBufferInfo.h>
-
+#include <private/backend/BackendUtils.h>
 #include <math/mat3.h>
 #include <utils/CString.h>
 #include <utils/Panic.h>
@@ -39,6 +39,7 @@
 #include <array>
 #include <cstddef>
 #include <cstdint>
+#include <memory>
 #include <sstream>
 #include <string_view>
 #include <utility>
@@ -234,6 +235,9 @@ WebGPUDriver::WebGPUDriver(WebGPUPlatform& platform, const Platform::DriverConfi
     printAdapterDetails(mAdapter);
 #endif
     mDevice = mPlatform.requestDevice(mAdapter);
+    wgpu::Limits supportedLimits{};
+    mDevice.GetLimits(&supportedLimits);
+    mMinUniformBufferOffsetAlignment = supportedLimits.minUniformBufferOffsetAlignment;
 #if FWGPU_ENABLED(FWGPU_PRINT_SYSTEM)
     printDeviceDetails(mDevice);
 #endif
@@ -350,6 +354,17 @@ void WebGPUDriver::destroyProgram(Handle<HwProgram> ph) {
 }
 
 void WebGPUDriver::destroyRenderTarget(Handle<HwRenderTarget> rth) {
+    if (rth) {
+        WGPURenderTarget* rt = handleCast<WGPURenderTarget>(rth);
+        if (rt == mDefaultRenderTarget) {
+            mDefaultRenderTarget = nullptr;
+        }
+        // WGPURenderTarget destructor is trivial.
+        // The HwTexture handles stored within WGPURenderTarget (via MRT, TargetBufferInfo)
+        // are not owned by WGPURenderTarget, so they are not destroyed here.
+        // They are destroyed via WebGPUDriver::destroyTexture.
+        destructHandle<WGPURenderTarget>(rth);
+    }
 }
 
 void WebGPUDriver::destroySwapChain(Handle<HwSwapChain> sch) {
@@ -468,11 +483,10 @@ void WebGPUDriver::createSwapChainR(Handle<HwSwapChain> sch, void* nativeWindow,
     mSwapChain = constructHandle<WebGPUSwapChain>(sch, std::move(surface), surfaceSize, mAdapter,
             mDevice, flags);
     assert_invariant(mSwapChain);
-    WebGPUDescriptorSet::initializeDummyResourcesIfNotAlready(mDevice,
+
-            mSwapChain->getColorFormat());
+    FWGPU_LOGW << "WebGPU support is highly experimental, in development, and tested for only a "
-    FWGPU_LOGW << "WebGPU support is still essentially a no-op at this point in development (only "
+                  "small set of simple samples (e.g. hellotriangle and texturedquad), thus issues "
-                  "background components have been instantiated/selected, such as surface/screen, "
+                  "are likely to be encountered at this stage."
-                  "graphics device/GPU, etc.), thus nothing is being drawn to the screen."
                << utils::io::endl;
 #if !FWGPU_ENABLED(FWGPU_PRINT_SYSTEM) && !defined(NDEBUG)
     FWGPU_LOGI << "If the FILAMENT_BACKEND_DEBUG_FLAG variable were set with the " << utils::io::hex
@@ -577,7 +591,21 @@ void WebGPUDriver::createDefaultRenderTargetR(Handle<HwRenderTarget> rth, int) {
 
 void WebGPUDriver::createRenderTargetR(Handle<HwRenderTarget> rth, TargetBufferFlags targets,
         uint32_t width, uint32_t height, uint8_t samples, uint8_t layerCount, MRT color,
-        TargetBufferInfo depth, TargetBufferInfo stencil) {}
+        TargetBufferInfo depth, TargetBufferInfo stencil) {
+    // The `targets` flags indicate which of the `color`, `depth`, `stencil` TargetBufferInfo
+    // are actually active for this render target.
+    // We'll pass all TargetBufferInfo to WGPURenderTarget; it will use them if their handles are valid.
+
+    // Ensure that textures intended for use as attachments were created with
+    // wgpu::TextureUsage::RenderAttachment. This check should ideally be in createTextureR
+    // or validated here if possible.
+
+    // The `layerCount` parameter might be for creating array textures that this RT targets.
+    // Individual attachments (color[i].layer, depth.layer, stencil.layer) specify which layer
+    // of an array texture to bind. For now, we assume textures are pre-configured.
+
+    constructHandle<WGPURenderTarget>(rth, width, height, samples, color, depth, stencil);
+}
 
 void WebGPUDriver::createFenceR(Handle<HwFence> fh, int) {}
 
@@ -721,17 +749,20 @@ size_t WebGPUDriver::getMaxArrayTextureLayers() {
 
 void WebGPUDriver::updateIndexBuffer(Handle<HwIndexBuffer> ibh, BufferDescriptor&& p,
         uint32_t byteOffset) {
-    updateGPUBuffer(handleCast<WGPUIndexBuffer>(ibh), std::move(p), byteOffset);
+    handleCast<WGPUIndexBuffer>(ibh)->updateGPUBuffer(p, byteOffset, mQueue);
+    scheduleDestroy(std::move(p));
 }
 
 void WebGPUDriver::updateBufferObject(Handle<HwBufferObject> ibh, BufferDescriptor&& p,
         uint32_t byteOffset) {
-    updateGPUBuffer(handleCast<WGPUBufferObject>(ibh), std::move(p), byteOffset);
+    handleCast<WGPUBufferObject>(ibh)->updateGPUBuffer(p, byteOffset, mQueue);
+    scheduleDestroy(std::move(p));
 }
 
 void WebGPUDriver::updateBufferObjectUnsynchronized(Handle<HwBufferObject> ibh,
         BufferDescriptor&& p, uint32_t byteOffset) {
-    updateGPUBuffer(handleCast<WGPUBufferObject>(ibh), std::move(p), byteOffset);
+    handleCast<WGPUBufferObject>(ibh)->updateGPUBuffer(p, byteOffset, mQueue);
+    scheduleDestroy(std::move(p));
 }
 
 void WebGPUDriver::resetBufferObject(Handle<HwBufferObject> boh) {
@@ -743,15 +774,76 @@ void WebGPUDriver::setVertexBufferObject(Handle<HwVertexBuffer> vbh, uint32_t in
     auto* vertexBuffer = handleCast<WGPUVertexBuffer>(vbh);
     auto* bufferObject = handleCast<WGPUBufferObject>(boh);
     assert_invariant(index < vertexBuffer->buffers.size());
-    assert_invariant(bufferObject->buffer.GetUsage() & wgpu::BufferUsage::Vertex);
+    assert_invariant(bufferObject->getBuffer().GetUsage() & wgpu::BufferUsage::Vertex);
-    vertexBuffer->buffers[index] = bufferObject->buffer;
+    vertexBuffer->buffers[index] = bufferObject->getBuffer();
 }
 
-void WebGPUDriver::update3DImage(Handle<HwTexture> th,
+void WebGPUDriver::update3DImage(Handle<HwTexture> th, uint32_t level, uint32_t xoffset,
-        uint32_t level, uint32_t xoffset, uint32_t yoffset, uint32_t zoffset,
+        uint32_t yoffset, uint32_t zoffset, uint32_t width, uint32_t height, uint32_t depth,
-        uint32_t width, uint32_t height, uint32_t depth,
+        PixelBufferDescriptor&& p) {
-        PixelBufferDescriptor&& data) {
+    PixelBufferDescriptor* data = &p;
-    scheduleDestroy(std::move(data));
+    PixelBufferDescriptor reshapedData;
+    if (reshape(p, reshapedData)) {
+        data = &reshapedData;
+    }
+    auto texture = handleCast<WGPUTexture>(th);
+
+    // TODO: Writing to a depth texture is illegal and errors. I'm not sure why Filament is trying
+    // to do so, but early returning is working?
+    if(texture->getAspect() == wgpu::TextureAspect::DepthOnly){
+        scheduleDestroy(std::move(p));
+        return;
+    }
+    size_t blockWidth = texture->getBlockWidth();
+    size_t blockHeight = texture->getBlockHeight();
+    // WebGPU specification requires that for compressed textures, the x and y offsets
+    // must be a multiple of the compressed texture format's block width and height.
+    // See: https://www.w3.org/TR/webgpu/#abstract-opdef-validating-gputexelcopytextureinfo
+    if (blockWidth > 1 || blockHeight > 1) {
+        FILAMENT_CHECK_PRECONDITION(xoffset % blockWidth == 0)
+                << "xoffset must be aligned to blockwidth, but offset is " << blockWidth
+                << "and offset is " << xoffset;
+        FILAMENT_CHECK_PRECONDITION(yoffset % blockHeight == 0)
+                << "yoffset must be aligned to blockHeight, but offset is " << blockHeight
+                << "and offset is " << yoffset;
+    }
+
+    auto copyInfo = wgpu::TexelCopyTextureInfo{ .texture = texture->getTexture(),
+        .mipLevel = level,
+        .origin = { .x = xoffset, .y = yoffset, .z = zoffset },
+        .aspect = texture->getAspect() };
+    uint32_t bytesPerRow = static_cast<uint32_t>(
+            PixelBufferDescriptor::computePixelSize(data->format, data->type) * width);
+    auto extent = wgpu::Extent3D{ .width = width, .height = height, .depthOrArrayLayers = depth };
+
+    const uint8_t* dataBuff = static_cast<const uint8_t*>(data->buffer);
+    size_t dataSize = data->size;
+    std::unique_ptr<uint8_t[]> paddedBuffer;
+
+    if (bytesPerRow % 256 != 0) {
+        uint32_t padding = 256 - (bytesPerRow % 256);
+        uint32_t paddedBytesPerRow = bytesPerRow + padding;
+
+        size_t paddedBufferSize = static_cast<size_t>(paddedBytesPerRow) * height * depth;
+        paddedBuffer = std::make_unique<uint8_t[]>(paddedBufferSize);
+        uint8_t* dest = paddedBuffer.get();
+
+        for (uint32_t z = 0; z < depth; ++z) {
+            for (uint32_t y = 0; y < height; ++y) {
+                std::memcpy(dest, dataBuff, bytesPerRow);
+                dest += paddedBytesPerRow;
+                dataBuff += bytesPerRow;
+            }
+        }
+        dataBuff = paddedBuffer.get();
+        dataSize = paddedBufferSize;
+        bytesPerRow = paddedBytesPerRow;
+    }
+
+    auto layout = wgpu::TexelCopyBufferLayout{ .bytesPerRow = bytesPerRow, .rowsPerImage = height };
+
+    mQueue.WriteTexture(&copyInfo, dataBuff, dataSize, &layout, &extent);
+    scheduleDestroy(std::move(p));
 }
 
 void WebGPUDriver::setupExternalImage(void* image) {
@@ -778,56 +870,74 @@ void WebGPUDriver::compilePrograms(CompilerPriorityQueue priority,
 
 void WebGPUDriver::beginRenderPass(Handle<HwRenderTarget> rth, RenderPassParams const& params) {
     assert_invariant(mCommandEncoder);
-
     auto* renderTarget = handleCast<WGPURenderTarget>(rth);
-    // if (renderTarget == mDefaultRenderTarget) {
+
-    //     FWGPU_LOGW << "Default render target"
+    wgpu::RenderPassDescriptor renderPassDescriptor{};
-    //                << utils::io::endl;
+    wgpu::TextureView defaultColorView = nullptr;
-    // } else {
+    wgpu::TextureView defaultDepthStencilView = nullptr;
-    //     FWGPU_LOGW << "Non Default render target"
+
-    //                << utils::io::endl;
+    std::array<wgpu::TextureView, MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT> customColorViews{};
-    // }
+    uint32_t customColorViewCount = 0;
-    wgpu::RenderPassDescriptor renderPassDescriptor2;
+    wgpu::TextureView customDepthView = nullptr;
-    wgpu::RenderPassDepthStencilAttachment depthStencilAttachment{
+    wgpu::TextureView customStencilView = nullptr;
-        .view = mSwapChain->getDepthTextureView(),
+
-        .depthLoadOp = WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::DEPTH),
+    if (renderTarget->isDefaultRenderTarget()) {
-        .depthStoreOp = WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::DEPTH),
+        assert_invariant(mSwapChain && mTextureView);
-        .depthClearValue = static_cast<float>(params.clearDepth),
+        defaultColorView = mTextureView;
-        .depthReadOnly = (params.readOnlyDepthStencil & RenderPassParams::READONLY_DEPTH) > 0,
+        defaultDepthStencilView = mSwapChain->getDepthTextureView();
-        .stencilLoadOp = WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::STENCIL),
-        .stencilStoreOp = WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::STENCIL),
-        .stencilClearValue = params.clearStencil,
-        .stencilReadOnly = (params.readOnlyDepthStencil & RenderPassParams::READONLY_STENCIL) > 0
-    };
-    renderTarget->setUpRenderPassAttachments(renderPassDescriptor2, mTextureView, params);
-    renderPassDescriptor2.depthStencilAttachment = &depthStencilAttachment;
-    // TODO: Remove this code once WebGPU pipeline is implemented
-    static float red = 1.0f;
-    if (red - 0.01 > 0) {
-        red -= 0.01;
     } else {
-        red = 1.0f;
+        // Resolve views for custom render target
+        const auto& colorInfos = renderTarget->getColorAttachmentInfos();
+        for (int i = 0; i < MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT; ++i) {
+            if (colorInfos[i].handle) {
+                auto* hwTexture = handleCast<WGPUTexture>(colorInfos[i].handle);
+                if (hwTexture) {
+                    // TODO: Consider colorInfos[i].level and colorInfos[i].layer for view creation
+                    // if WGPUTexture::getTexView() isn't sufficient or needs parameters.
+                    customColorViews[customColorViewCount++] = hwTexture->getTexView();
+                }
+            }
+        }
+
+        const auto& depthInfo = renderTarget->getDepthAttachmentInfo();
+        if (depthInfo.handle) {
+            auto* hwTexture = handleCast<WGPUTexture>(depthInfo.handle);
+            if (hwTexture) {
+                customDepthView = hwTexture->getTexView();
+            }
+        }
+
+        const auto& stencilInfo = renderTarget->getStencilAttachmentInfo();
+        if (stencilInfo.handle) {
+            // If depth and stencil use the same texture handle, this will re-cast but that's fine.
+            auto* hwTexture = handleCast<WGPUTexture>(stencilInfo.handle);
+            if (hwTexture) {
+                customStencilView = hwTexture->getTexView();
+            }
+        }
     }
-    assert_invariant(mTextureView);
-    wgpu::RenderPassColorAttachment renderPassColorAttachment = {
-        .view = mTextureView,
-        // TODO: remove this code once WebGPU Pipeline is implemented with render targets, pipeline and buffers.
-        .depthSlice = wgpu::kDepthSliceUndefined,
-        .loadOp = wgpu::LoadOp::Clear,
-        .storeOp = wgpu::StoreOp::Store,
-        .clearValue = wgpu::Color{red, 0 , 0 , 1},
-    };
 
-    wgpu::RenderPassDescriptor renderPassDescriptor = {
+    renderTarget->setUpRenderPassAttachments(renderPassDescriptor,
-        .colorAttachmentCount = 1,
+            params,
-        .colorAttachments = &renderPassColorAttachment,
+            defaultColorView,
-        .depthStencilAttachment = nullptr,
+            defaultDepthStencilView,
-        .timestampWrites = nullptr,
+            customColorViews.data(),
-    };
+            customColorViewCount,
+            customDepthView,
+            customStencilView);
 
-    mRenderPassEncoder = mCommandEncoder.BeginRenderPass(&renderPassDescriptor2);
+    mRenderPassEncoder = mCommandEncoder.BeginRenderPass(&renderPassDescriptor);
-    mRenderPassEncoder.SetViewport(params.viewport.left, params.viewport.bottom,
+    // Ensure viewport dimensions are positive
-            params.viewport.width, params.viewport.height, params.depthRange.near, params.depthRange.far);
+    uint32_t viewportWidth = params.viewport.width > 0 ? params.viewport.width : 1;
+    uint32_t viewportHeight = params.viewport.height > 0 ? params.viewport.height : 1;
+
+    mRenderPassEncoder.SetViewport(
+            static_cast<float>(params.viewport.left),
+            static_cast<float>(params.viewport.bottom),
+            static_cast<float>(viewportWidth),
+            static_cast<float>(viewportHeight),
+            params.depthRange.near,
+            params.depthRange.far);
 }
 
 void WebGPUDriver::endRenderPass(int /* dummy */) {
@@ -916,6 +1026,14 @@ void WebGPUDriver::blit(
 }
 
 void WebGPUDriver::bindPipeline(PipelineState const& pipelineState) {
+    // TODO Investigate implications of this hash more closely. Vulkan has a whole class
+    // VulkanPipelineCache to handle this, may be missing nuance
+    static auto pipleineStateHasher = utils::hash::MurmurHashFn<filament::backend::PipelineState>();
+    auto hash = pipleineStateHasher(pipelineState);
+    if(mPipelineMap.find(hash) != mPipelineMap.end()){
+        mRenderPassEncoder.SetPipeline(mPipelineMap[hash]);
+        return;
+    }
     const auto* program = handleCast<WGPUProgram>(pipelineState.program);
     assert_invariant(program);
     assert_invariant(program->computeShaderModule == nullptr &&
@@ -952,7 +1070,7 @@ void WebGPUDriver::bindPipeline(PipelineState const& pipelineState) {
             *vertexBufferInfo, layout, pipelineState.rasterState, pipelineState.stencilState,
             pipelineState.polygonOffset, pipelineState.primitiveType, mSwapChain->getColorFormat(),
             mSwapChain->getDepthFormat());
-    // TODO: uncomment once we have a valid pipeline to set
+    mPipelineMap[hash] = pipeline;
     mRenderPassEncoder.SetPipeline(pipeline);
 }
 
@@ -968,18 +1086,12 @@ void WebGPUDriver::bindRenderPrimitive(Handle<HwRenderPrimitive> rph) {
         mRenderPassEncoder.SetVertexBuffer(i, renderPrimitive->vertexBuffer->buffers[i]);
     }
 
-    mRenderPassEncoder.SetIndexBuffer(renderPrimitive->indexBuffer->buffer,
+    mRenderPassEncoder.SetIndexBuffer(renderPrimitive->indexBuffer->getBuffer(),
             renderPrimitive->indexBuffer->indexFormat);
 }
 
 void WebGPUDriver::draw2(uint32_t indexOffset, uint32_t indexCount, uint32_t instanceCount) {
-    // Calling DrawIndexed with "firstInstance = 0" results in a NON spinning triangle
+    mRenderPassEncoder.DrawIndexed(indexCount, instanceCount, indexOffset, 0, 0);
-    //    mRenderPassEncoder.DrawIndexed(indexCount, instanceCount, indexOffset, 0, 0);
-    // Calling DrawIndexed with "firstInstance = 1" results in a spinning triangle
-    mRenderPassEncoder.DrawIndexed(indexCount, instanceCount, indexOffset, 0, 1);
-    // Calling Draw with "firstInstance = 0" results in a NON spinning triangle
-    // Calling Draw with "firstInstance = 1" results in a spinning triangle
-    //    mRenderPassEncoder.Draw(indexCount, instanceCount, 0, 1);
 }
 
 void WebGPUDriver::draw(PipelineState, Handle<HwRenderPrimitive>, uint32_t indexOffset,
@@ -1010,8 +1122,11 @@ void WebGPUDriver::updateDescriptorSetBuffer(Handle<HwDescriptorSet> dsh,
     auto buffer = handleCast<WGPUBufferObject>(boh);
     if (!bindGroup->getIsLocked()) {
         // TODO making assumptions that size and offset mean the same thing here.
+        FILAMENT_CHECK_PRECONDITION(offset % mMinUniformBufferOffsetAlignment == 0)
+                << "Binding offset must be multiple of " << mMinUniformBufferOffsetAlignment
+                << "But requested offset is " << offset;
         wgpu::BindGroupEntry entry{ .binding = static_cast<uint32_t>(binding * 2),
-            .buffer = buffer->buffer,
+            .buffer = buffer->getBuffer(),
             .offset = offset,
             .size = size };
         bindGroup->addEntry(entry.binding, std::move(entry));
@@ -1043,115 +1158,105 @@ void WebGPUDriver::bindDescriptorSet(Handle<HwDescriptorSet> dsh,
     const auto bindGroup = handleCast<WebGPUDescriptorSet>(dsh);
     const auto wbg = bindGroup->lockAndReturn(mDevice);
     assert_invariant(mRenderPassEncoder);
-    // TODO is this how we should be getting the dynamic offsets?
-    //      should we add offsets for unused entries or is the input already have them?
-    //      this implementation assumes unused entries are not provided, and adds dummy values.
-    //      The count also includes unused entities, as not doing so produces errors
     const size_t dynamicOffsetCount = bindGroup->countEntitiesWithDynamicOffsets();
-    uint32_t const* const dynamicOffsetsWithUnused = bindGroup->setDynamicOffsets(offsets.data());
+    mRenderPassEncoder.SetBindGroup(setIndex, wbg, dynamicOffsetCount, offsets.data());
-    mRenderPassEncoder.SetBindGroup(setIndex, wbg, dynamicOffsetCount, dynamicOffsetsWithUnused);
 }
 
 void WebGPUDriver::setDebugTag(HandleBase::HandleId handleId, utils::CString tag) {
 }
 wgpu::Sampler WebGPUDriver::makeSampler(SamplerParams const& params) {
-    wgpu::SamplerDescriptor desc;
+    wgpu::SamplerDescriptor desc{};
 
     desc.label = "TODO";
     desc.addressModeU = fWrapModeToWAddressMode(params.wrapS);
     desc.addressModeV = fWrapModeToWAddressMode(params.wrapR);
     desc.addressModeW = fWrapModeToWAddressMode(params.wrapT);
-    switch (params.filterMag) {
+    if (params.compareMode == SamplerCompareMode::COMPARE_TO_TEXTURE) {
-        case SamplerMagFilter::NEAREST: {
+        switch (params.filterMag) {
-            desc.magFilter = wgpu::FilterMode::Nearest;
+            case SamplerMagFilter::NEAREST: {
-            break;
+                desc.magFilter = wgpu::FilterMode::Nearest;
+                break;
+            }
+            case SamplerMagFilter::LINEAR: {
+                desc.magFilter = wgpu::FilterMode::Linear;
+                break;
+            }
         }
-        case SamplerMagFilter::LINEAR: {
+        switch (params.filterMin) {
-            desc.magFilter = wgpu::FilterMode::Linear;
+            case SamplerMinFilter::NEAREST: {
-            break;
+                desc.minFilter = wgpu::FilterMode::Nearest;
-        }
+                desc.mipmapFilter = wgpu::MipmapFilterMode::Undefined;
-    }
+                break;
-    switch (params.filterMin) {
+            }
-        case SamplerMinFilter::NEAREST: {
+            case SamplerMinFilter::LINEAR: {
-            desc.minFilter = wgpu::FilterMode::Nearest;
+                desc.minFilter = wgpu::FilterMode::Linear;
-            // Metal Driver uses an explicit not-mipmapped value webgpu lacks. Nearest should
+                desc.mipmapFilter = wgpu::MipmapFilterMode::Undefined;
-            // suffice
+                break;
-            desc.mipmapFilter = wgpu::MipmapFilterMode::Nearest;
+            }
-            break;
+            case SamplerMinFilter::NEAREST_MIPMAP_NEAREST: {
-        }
+                desc.minFilter = wgpu::FilterMode::Nearest;
-        case SamplerMinFilter::LINEAR: {
+                desc.mipmapFilter = wgpu::MipmapFilterMode::Nearest;
-            desc.minFilter = wgpu::FilterMode::Linear;
+                break;
-            // Metal Driver uses an explicit not-mipmapped value webgpu lacks. Nearest should
+            }
-            // suffice
+            case SamplerMinFilter::LINEAR_MIPMAP_NEAREST: {
+                desc.minFilter = wgpu::FilterMode::Linear;
+                desc.mipmapFilter = wgpu::MipmapFilterMode::Nearest;
 
-            desc.mipmapFilter = wgpu::MipmapFilterMode::Nearest;
+                break;
-            break;
+            }
-        }
+            case SamplerMinFilter::NEAREST_MIPMAP_LINEAR: {
-        case SamplerMinFilter::NEAREST_MIPMAP_NEAREST: {
+                desc.minFilter = wgpu::FilterMode::Nearest;
-            desc.minFilter = wgpu::FilterMode::Nearest;
+                desc.mipmapFilter = wgpu::MipmapFilterMode::Linear;
-            desc.mipmapFilter = wgpu::MipmapFilterMode::Nearest;
-            break;
-        }
-        case SamplerMinFilter::LINEAR_MIPMAP_NEAREST: {
-            desc.minFilter = wgpu::FilterMode::Linear;
-            desc.mipmapFilter = wgpu::MipmapFilterMode::Nearest;
 
-            break;
+                break;
+            }
+            case SamplerMinFilter::LINEAR_MIPMAP_LINEAR: {
+                desc.minFilter = wgpu::FilterMode::Linear;
+                desc.mipmapFilter = wgpu::MipmapFilterMode::Linear;
+                break;
+            }
         }
-        case SamplerMinFilter::NEAREST_MIPMAP_LINEAR: {
+        switch (params.compareFunc) {
-            desc.minFilter = wgpu::FilterMode::Nearest;
+            case SamplerCompareFunc::LE: {
-            desc.mipmapFilter = wgpu::MipmapFilterMode::Linear;
+                desc.compare = wgpu::CompareFunction::LessEqual;
-
+                break;
-            break;
+            }
-        }
+            case SamplerCompareFunc::GE: {
-        case SamplerMinFilter::LINEAR_MIPMAP_LINEAR: {
+                desc.compare = wgpu::CompareFunction::GreaterEqual;
-            desc.minFilter = wgpu::FilterMode::Linear;
+                break;
-            desc.mipmapFilter = wgpu::MipmapFilterMode::Linear;
+            }
-            break;
+            case SamplerCompareFunc::L: {
-        }
+                desc.compare = wgpu::CompareFunction::Less;
-    }
+                break;
-    switch (params.compareFunc) {
+            }
-        case SamplerCompareFunc::LE: {
+            case SamplerCompareFunc::G: {
-            desc.compare = wgpu::CompareFunction::LessEqual;
+                desc.compare = wgpu::CompareFunction::Greater;
-            break;
+                break;
-        }
+            }
-        case SamplerCompareFunc::GE: {
+            case SamplerCompareFunc::E: {
-            desc.compare = wgpu::CompareFunction::GreaterEqual;
+                desc.compare = wgpu::CompareFunction::Equal;
-            break;
+                break;
-        }
+            }
-        case SamplerCompareFunc::L: {
+            case SamplerCompareFunc::NE: {
-            desc.compare = wgpu::CompareFunction::Less;
+                desc.compare = wgpu::CompareFunction::NotEqual;
-            break;
+                break;
-        }
+            }
-        case SamplerCompareFunc::G: {
+            case SamplerCompareFunc::A: {
-            desc.compare = wgpu::CompareFunction::Greater;
+                desc.compare = wgpu::CompareFunction::Always;
-            break;
+                break;
-        }
+            }
-        case SamplerCompareFunc::E: {
+            case SamplerCompareFunc::N: {
-            desc.compare = wgpu::CompareFunction::Equal;
+                desc.compare = wgpu::CompareFunction::Never;
-            break;
+                break;
-        }
+            }
-        case SamplerCompareFunc::NE: {
-            desc.compare = wgpu::CompareFunction::NotEqual;
-            break;
-        }
-        case SamplerCompareFunc::A: {
-            desc.compare = wgpu::CompareFunction::Always;
-            break;
-        }
-        case SamplerCompareFunc::N: {
-            desc.compare = wgpu::CompareFunction::Never;
-            break;
         }
     }
 
     desc.maxAnisotropy = 1u << params.anisotropyLog2;
 
+    // Unused: WGPU lodMinClamp/lodMaxClamp unnecessary
 
-    // Unused: Filament's compareMode, WGPU lodMinClamp/lodMaxClamp
+    return mDevice.CreateSampler(&desc);
-
-    //TODO Once we can properly map to descriptorsetlayout use the sampler.
-    return mDevice.CreateSampler(/*&desc*/);
 }
 wgpu::AddressMode WebGPUDriver::fWrapModeToWAddressMode(const SamplerWrapMode& fWrapMode) {
     switch (fWrapMode) {
@@ -1171,5 +1276,4 @@ wgpu::AddressMode WebGPUDriver::fWrapModeToWAddressMode(const SamplerWrapMode& f
     return wgpu::AddressMode::Undefined;
 }
 
-
 } // namespace filament

filament/backend/src/webgpu/WebGPUDriver.h

@@ -58,32 +58,13 @@ private:
     [[nodiscard]] ShaderLanguage getShaderLanguage() const noexcept final;
     [[nodiscard]] wgpu::Sampler makeSampler(SamplerParams const& params);
     [[nodiscard]] static wgpu::AddressMode fWrapModeToWAddressMode(const filament::backend::SamplerWrapMode& fUsage);
-    template<typename GPUBufferObject>
-    void updateGPUBuffer(GPUBufferObject* gpuBufferObject, BufferDescriptor&& bufferDescriptor,
-            uint32_t byteOffset) {
-        FILAMENT_CHECK_PRECONDITION(bufferDescriptor.buffer)
-                << "copyIntoBuffer called with a null buffer";
-        FILAMENT_CHECK_PRECONDITION(
-                bufferDescriptor.size + byteOffset <= gpuBufferObject->buffer.GetSize())
-                << "Attempting to copy " << bufferDescriptor.size << " bytes into a buffer of size "
-                << gpuBufferObject->buffer.GetSize() << " at offset " << byteOffset;
-
-        // TODO: All buffer objects are created with CopyDst usage.
-        // This may have some performance implications. That should be investigated later.
-        assert_invariant(gpuBufferObject->buffer.GetUsage() & wgpu::BufferUsage::CopyDst);
-
-        // WriteBuffer is an async call. But cpu buffer data is already written to the staging
-        // buffer on return from the WriteBuffer.
-        mQueue.WriteBuffer(gpuBufferObject->buffer, byteOffset, bufferDescriptor.buffer,
-                bufferDescriptor.size);
-        scheduleDestroy(std::move(bufferDescriptor));
-    }
 
     // the platform (e.g. OS) specific aspects of the WebGPU backend are strictly only
     // handled in the WebGPUPlatform
     WebGPUPlatform& mPlatform;
     wgpu::Adapter mAdapter = nullptr;
     wgpu::Device mDevice = nullptr;
+    uint32_t mMinUniformBufferOffsetAlignment;
     wgpu::Queue mQueue = nullptr;
     void* mNativeWindow = nullptr;
     WebGPUSwapChain* mSwapChain = nullptr;
@@ -93,6 +74,8 @@ private:
     wgpu::RenderPassEncoder mRenderPassEncoder = nullptr;
     wgpu::CommandBuffer mCommandBuffer = nullptr;
     WGPURenderTarget* mDefaultRenderTarget = nullptr;
+
+    tsl::robin_map<uint32_t, wgpu::RenderPipeline> mPipelineMap;
     /*
      * Driver interface
      */

filament/backend/src/webgpu/WebGPUHandles.cpp

@@ -19,7 +19,8 @@
 #include <backend/DriverEnums.h>
 
 #include <utils/BitmaskEnum.h>
-
+#include <utils/Panic.h>
+#include <private/backend/BackendUtils.h>
 #include <webgpu/webgpu_cpp.h>
 
 #include <algorithm>
@@ -40,15 +41,6 @@ constexpr wgpu::BufferUsage getBufferObjectUsage(
     }
 }
 
-wgpu::Buffer createBuffer(wgpu::Device const& device, wgpu::BufferUsage usage, uint32_t size,
-        char const* label) {
-    wgpu::BufferDescriptor descriptor{ .label = label,
-        .usage = usage,
-        .size = size,
-        .mappedAtCreation = false };
-    return device.CreateBuffer(&descriptor);
-}
-
 wgpu::VertexFormat getVertexFormat(filament::backend::ElementType type, bool normalized, bool integer) {
     using ElementType = filament::backend::ElementType;
     using VertexFormat = wgpu::VertexFormat;
@@ -76,7 +68,7 @@ wgpu::VertexFormat getVertexFormat(filament::backend::ElementType type, bool nor
             case ElementType::BYTE4: return VertexFormat::Snorm8x4;
             case ElementType::UBYTE4: return VertexFormat::Unorm8x4;
             case ElementType::SHORT4: return VertexFormat::Snorm16x4;
-            case ElementType::USHORT4: return VertexFormat::Unorm8x4;
+            case ElementType::USHORT4: return VertexFormat::Unorm16x4;
             default:
                 FILAMENT_CHECK_POSTCONDITION(false) << "Normalized format does not exist.";
                 return VertexFormat::Float32x3;
@@ -119,10 +111,91 @@ wgpu::VertexFormat getVertexFormat(filament::backend::ElementType type, bool nor
     }
 }
 
+wgpu::StringView getUserTextureLabel(filament::backend::SamplerType target) {
+    // TODO will be helpful to get more useful info than this
+    using filament::backend::SamplerType;
+    switch (target) {
+        case SamplerType::SAMPLER_2D:
+            return "a_2D_user_texture";
+        case SamplerType::SAMPLER_2D_ARRAY:
+            return "a_2D_array_user_texture";
+        case SamplerType::SAMPLER_CUBEMAP:
+            return "a_cube_map_user_texture";
+        case SamplerType::SAMPLER_EXTERNAL:
+            return "an_external_user_texture";
+        case SamplerType::SAMPLER_3D:
+            return "a_3D_user_texture";
+        case SamplerType::SAMPLER_CUBEMAP_ARRAY:
+            return "a_cube_map_array_user_texture";
+    }
+}
+
+wgpu::StringView getUserTextureViewLabel(filament::backend::SamplerType target) {
+    // TODO will be helpful to get more useful info than this
+    using filament::backend::SamplerType;
+    switch (target) {
+        case SamplerType::SAMPLER_2D:
+            return "a_2D_user_texture_view";
+        case SamplerType::SAMPLER_2D_ARRAY:
+            return "a_2D_array_user_texture_view";
+        case SamplerType::SAMPLER_CUBEMAP:
+            return "a_cube_map_user_texture_view";
+        case SamplerType::SAMPLER_EXTERNAL:
+            return "an_external_user_texture_view";
+        case SamplerType::SAMPLER_3D:
+            return "a_3D_user_texture_view";
+        case SamplerType::SAMPLER_CUBEMAP_ARRAY:
+            return "a_cube_map_array_user_texture_view";
+    }
+}
+
 }// namespace
 
 namespace filament::backend {
 
+void WGPUBufferBase::createBuffer(const wgpu::Device& device, wgpu::BufferUsage usage,
+        uint32_t size, const char* label) {
+    // Write size must be divisible by 4. If the whole buffer is written to as is common, so must
+    // the buffer size.
+    size += (4 - (size % 4)) % 4;
+    wgpu::BufferDescriptor descriptor{ .label = label,
+        .usage = usage,
+        .size = size,
+        .mappedAtCreation = false };
+    buffer = device.CreateBuffer(&descriptor);
+}
+
+void WGPUBufferBase::updateGPUBuffer(BufferDescriptor& bufferDescriptor, uint32_t byteOffset,
+        wgpu::Queue queue) {
+    FILAMENT_CHECK_PRECONDITION(bufferDescriptor.buffer)
+            << "copyIntoBuffer called with a null buffer";
+    FILAMENT_CHECK_PRECONDITION(bufferDescriptor.size + byteOffset <= buffer.GetSize())
+            << "Attempting to copy " << bufferDescriptor.size << " bytes into a buffer of size "
+            << buffer.GetSize() << " at offset " << byteOffset;
+    FILAMENT_CHECK_PRECONDITION(byteOffset % 4 == 0)
+            << "Byte offset must be a multiple of 4 but is " << byteOffset;
+
+    // TODO: All buffer objects are created with CopyDst usage.
+    // This may have some performance implications. That should be investigated later.
+    assert_invariant(buffer.GetUsage() & wgpu::BufferUsage::CopyDst);
+
+    size_t remainder = bufferDescriptor.size % 4;
+
+    // WriteBuffer is an async call. But cpu buffer data is already written to the staging
+    // buffer on return from the WriteBuffer.
+    auto legalSize = bufferDescriptor.size - remainder;
+    queue.WriteBuffer(buffer, byteOffset, bufferDescriptor.buffer, legalSize);
+    if (remainder != 0) {
+        const uint8_t* remainderStart =
+                static_cast<const uint8_t*>(bufferDescriptor.buffer) + legalSize;
+        memcpy(mRemainderChunk.data(), remainderStart, remainder);
+        // Pad the remainder with zeros to ensure deterministic behavior, though GPU shouldn't
+        // access this
+        std::memset(mRemainderChunk.data() + remainder, 0, 4 - remainder);
+
+        queue.WriteBuffer(buffer, byteOffset + legalSize, &mRemainderChunk, 4);
+    }
+}
 WGPUVertexBufferInfo::WGPUVertexBufferInfo(uint8_t bufferCount, uint8_t attributeCount,
         AttributeArray const& attributes)
     : HwVertexBufferInfo(bufferCount, attributeCount),
@@ -165,9 +238,10 @@ WGPUVertexBufferInfo::WGPUVertexBufferInfo(uint8_t bufferCount, uint8_t attribut
 
 WGPUIndexBuffer::WGPUIndexBuffer(wgpu::Device const& device, uint8_t elementSize,
         uint32_t indexCount)
-    : buffer(createBuffer(device, wgpu::BufferUsage::CopyDst | wgpu::BufferUsage::Index,
+    : indexFormat(elementSize == 2 ? wgpu::IndexFormat::Uint16 : wgpu::IndexFormat::Uint32) {
-              elementSize * indexCount, "index_buffer")),
+    createBuffer(device, wgpu::BufferUsage::CopyDst | wgpu::BufferUsage::Index,
-      indexFormat(elementSize == 2 ? wgpu::IndexFormat::Uint16 : wgpu::IndexFormat::Uint32) {}
+            elementSize * indexCount, "index_buffer");
+}
 
 
 WGPUVertexBuffer::WGPUVertexBuffer(wgpu::Device const& device, uint32_t vertexCount,
@@ -178,10 +252,10 @@ WGPUVertexBuffer::WGPUVertexBuffer(wgpu::Device const& device, uint32_t vertexCo
 
 WGPUBufferObject::WGPUBufferObject(wgpu::Device const& device, BufferObjectBinding bindingType,
         uint32_t byteCount)
-    : HwBufferObject(byteCount),
+    : HwBufferObject(byteCount) {
-      buffer(createBuffer(device, wgpu::BufferUsage::CopyDst | getBufferObjectUsage(bindingType),
+    createBuffer(device, wgpu::BufferUsage::CopyDst | getBufferObjectUsage(bindingType), byteCount,
-              byteCount, "buffer_object")),
+            "buffer_object");
-      bufferObjectBinding(bindingType) {}
+}
 
 wgpu::ShaderStage WebGPUDescriptorSetLayout::filamentStageToWGPUStage(ShaderStageFlags fFlags) {
     wgpu::ShaderStage retStages = wgpu::ShaderStage::None;
@@ -201,14 +275,22 @@ WebGPUDescriptorSetLayout::WebGPUDescriptorSetLayout(DescriptorSetLayout const&
         wgpu::Device const& device) {
     assert_invariant(device);
 
+    std::string baseLabel;
+    if (std::holds_alternative<utils::StaticString>(layout.label)) {
+        const auto& temp = std::get_if<utils::StaticString>(&layout.label);
+        baseLabel = temp->c_str();
+    } else if (std::holds_alternative<utils::CString>(layout.label)) {
+        const auto& temp = std::get_if<utils::CString>(&layout.label);
+        baseLabel = temp->c_str();
+    }
+
     // TODO: layoutDescriptor has a "Label". Ideally we can get info on what this layout is for
     // debugging. For now, hack an incrementing value.
     static int layoutNum = 0;
 
     unsigned int samplerCount =
             std::count_if(layout.bindings.begin(), layout.bindings.end(), [](auto& fEntry) {
-                return fEntry.type == DescriptorType::SAMPLER ||
+                return DescriptorSetLayoutBinding::isSampler(fEntry.type);
-                       fEntry.type == DescriptorType::SAMPLER_EXTERNAL;
             });
 
 
@@ -224,18 +306,44 @@ WebGPUDescriptorSetLayout::WebGPUDescriptorSetLayout(DescriptorSetLayout const&
         entryInfo.binding = wEntry.binding;
 
         switch (fEntry.type) {
-            case DescriptorType::SAMPLER_EXTERNAL:
+            case DescriptorType::SAMPLER_2D_FLOAT:
-            case DescriptorType::SAMPLER: {
+            case DescriptorType::SAMPLER_2D_INT:
+            case DescriptorType::SAMPLER_2D_UINT:
+            case DescriptorType::SAMPLER_2D_DEPTH:
+            case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_2D_ARRAY_INT:
+            case DescriptorType::SAMPLER_2D_ARRAY_UINT:
+            case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
+            case DescriptorType::SAMPLER_CUBE_FLOAT:
+            case DescriptorType::SAMPLER_CUBE_INT:
+            case DescriptorType::SAMPLER_CUBE_UINT:
+            case DescriptorType::SAMPLER_CUBE_DEPTH:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
+            case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
+            case DescriptorType::SAMPLER_3D_FLOAT:
+            case DescriptorType::SAMPLER_3D_INT:
+            case DescriptorType::SAMPLER_3D_UINT:
+            case DescriptorType::SAMPLER_2D_MS_FLOAT:
+            case DescriptorType::SAMPLER_2D_MS_INT:
+            case DescriptorType::SAMPLER_2D_MS_UINT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
+            case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT: {
                 auto& samplerEntry = wEntries.emplace_back();
                 auto& samplerEntryInfo = mBindGroupEntries.emplace_back();
                 samplerEntry.binding = fEntry.binding * 2 + 1;
                 samplerEntryInfo.binding = samplerEntry.binding;
-                samplerEntryInfo.type = WebGPUDescriptorSetLayout::BindGroupEntryType::SAMPLER;
                 samplerEntry.visibility = wEntry.visibility;
-                // We are simply hoping that undefined and defaults suffices here.
+                wEntry.texture.multisampled = isMultiSampledTypeDescriptor(fEntry.type);
-                samplerEntry.sampler.type = wgpu::SamplerBindingType::NonFiltering; // Example default
+                // TODO: Set once we have the filtering values
-                wEntry.texture.sampleType = wgpu::TextureSampleType::Float;      // Example default
+                if (isDepthDescriptor(fEntry.type)) {
-                entryInfo.type = WebGPUDescriptorSetLayout::BindGroupEntryType::TEXTURE_VIEW;
+                    samplerEntry.sampler.type = wgpu::SamplerBindingType::Comparison;
+                } else {
+                    samplerEntry.sampler.type =
+                            wgpu::SamplerBindingType::NonFiltering;
+                }
                 break;
             }
             case DescriptorType::UNIFORM_BUFFER: {
@@ -246,7 +354,6 @@ WebGPUDescriptorSetLayout::WebGPUDescriptorSetLayout(DescriptorSetLayout const&
                 // TODO: Ideally we fill minBindingSize
                 break;
             }
-
             case DescriptorType::INPUT_ATTACHMENT: {
                 PANIC_POSTCONDITION("Input Attachment is not supported");
                 break;
@@ -255,10 +362,52 @@ WebGPUDescriptorSetLayout::WebGPUDescriptorSetLayout(DescriptorSetLayout const&
                 PANIC_POSTCONDITION("Shader storage is not supported");
                 break;
             }
+            case DescriptorType::SAMPLER_EXTERNAL: {
+                PANIC_POSTCONDITION("External Sampler is not supported");
+                break;
+            }
+        }
+        if (isDepthDescriptor(fEntry.type))
+        {
+            wEntry.texture.sampleType = wgpu::TextureSampleType::Depth;
+        }
+        else if (isFloatDescriptor(fEntry.type))
+        {
+            // TODO: Set once we have the filtering values
+            wEntry.texture.sampleType = wgpu::TextureSampleType::UnfilterableFloat;
+        }
+        else if (isIntDescriptor(fEntry.type))
+        {
+            wEntry.texture.sampleType = wgpu::TextureSampleType::Sint;
+        }
+        else if (isUnsignedIntDescriptor(fEntry.type))
+        {
+            wEntry.texture.sampleType = wgpu::TextureSampleType::Uint;
+        }
+
+        if (is3dTypeDescriptor(fEntry.type))
+        {
+            wEntry.texture.viewDimension = wgpu::TextureViewDimension::e3D;
+        }
+        else if (is2dTypeDescriptor(fEntry.type))
+        {
+            wEntry.texture.viewDimension = wgpu::TextureViewDimension::e2D;
+        }
+        else if (is2dArrayTypeDescriptor(fEntry.type))
+        {
+            wEntry.texture.viewDimension = wgpu::TextureViewDimension::e2DArray;
+        }
+        else if (isCubeTypeDescriptor(fEntry.type))
+        {
+            wEntry.texture.viewDimension = wgpu::TextureViewDimension::Cube;
+        }
+        else if (isCubeArrayTypeDescriptor(fEntry.type))
+        {
+            wEntry.texture.viewDimension = wgpu::TextureViewDimension::CubeArray;
         }
         // fEntry.count is unused currently
     }
-    std::string label =  "layout_"+ std::to_string(++layoutNum) ;
+    std::string label =  "layout_" + baseLabel + std::to_string(++layoutNum) ;
     wgpu::BindGroupLayoutDescriptor layoutDescriptor{
         .label{label.c_str()}, // Use .c_str() if label needs to be const char*
         .entryCount = wEntries.size(),
@@ -269,114 +418,26 @@ WebGPUDescriptorSetLayout::WebGPUDescriptorSetLayout(DescriptorSetLayout const&
 
 WebGPUDescriptorSetLayout::~WebGPUDescriptorSetLayout() {}
 
-wgpu::Buffer WebGPUDescriptorSet::sDummyUniformBuffer = nullptr;
-wgpu::Texture WebGPUDescriptorSet::sDummyTexture = nullptr;
-wgpu::TextureView WebGPUDescriptorSet::sDummyTextureView = nullptr;
-wgpu::Sampler WebGPUDescriptorSet::sDummySampler = nullptr;
-
-void WebGPUDescriptorSet::initializeDummyResourcesIfNotAlready(wgpu::Device const& device,
-        wgpu::TextureFormat aColorFormat) {
-    if (!sDummyUniformBuffer) {
-        wgpu::BufferDescriptor bufferDescriptor{
-            .label = "dummy_uniform_not_to_be_used",
-            .usage = wgpu::BufferUsage::Uniform,
-            .size = 4
-        };
-        sDummyUniformBuffer = device.CreateBuffer(&bufferDescriptor);
-        FILAMENT_CHECK_POSTCONDITION(sDummyUniformBuffer)
-                << "Failed to create dummy uniform buffer?";
-    }
-    if (!sDummyTexture || !sDummyTextureView) {
-        wgpu::TextureDescriptor textureDescriptor{
-            .label = "dummy_texture_not_to_be_used",
-            .usage = wgpu::TextureUsage::TextureBinding,
-            .dimension = wgpu::TextureDimension::e2D,
-            .size = wgpu::Extent3D{ .width = 4, .height = 4, .depthOrArrayLayers = 1 },
-            .format = aColorFormat,
-        };
-        if (!sDummyTexture) {
-            sDummyTexture = device.CreateTexture(&textureDescriptor);
-            FILAMENT_CHECK_POSTCONDITION(sDummyUniformBuffer) << "Failed to create dummy texture?";
-        }
-        if (!sDummyTextureView) {
-            wgpu::TextureViewDescriptor textureViewDescriptor{
-                .label = "dummy_texture_view_not_to_be_used"
-            };
-            sDummyTextureView = sDummyTexture.CreateView(&textureViewDescriptor);
-            FILAMENT_CHECK_POSTCONDITION(sDummyUniformBuffer)
-                    << "Failed to create dummy texture view?";
-        }
-    }
-    if (!sDummySampler) {
-        wgpu::SamplerDescriptor samplerDescriptor{
-            .label = "dummy_sampler_not_to_be_used"
-        };
-        sDummySampler = device.CreateSampler(&samplerDescriptor);
-        FILAMENT_CHECK_POSTCONDITION(sDummyUniformBuffer) << "Failed to create dummy sampler?";
-    }
-}
-
-std::vector<wgpu::BindGroupEntry> WebGPUDescriptorSet::createDummyEntriesSortedByBinding(
-        std::vector<filament::backend::WebGPUDescriptorSetLayout::BindGroupEntryInfo> const&
-                bindGroupEntries) {
-    assert_invariant(WebGPUDescriptorSet::sDummyUniformBuffer &&
-                     "Dummy uniform buffer must have been created before "
-                     "creating dummy bind group entries.");
-    assert_invariant(
-            WebGPUDescriptorSet::sDummyTexture &&
-            "Dummy texture must have been created before creating dummy bind group entries.");
-    assert_invariant(
-            WebGPUDescriptorSet::sDummyTextureView &&
-            "Dummy texture view must have been created before creating dummy bind group entries.");
-    assert_invariant(
-            WebGPUDescriptorSet::sDummySampler &&
-            "Dummy sampler must have been created before creating dummy bind group entries.");
-    using filament::backend::WebGPUDescriptorSetLayout;
-    std::vector<wgpu::BindGroupEntry> entries;
-    entries.reserve(bindGroupEntries.size());
-    for (auto const& entryInfo: bindGroupEntries) {
-        auto& entry = entries.emplace_back();
-        entry.binding = entryInfo.binding;
-        switch (entryInfo.type) {
-            case WebGPUDescriptorSetLayout::BindGroupEntryType::UNIFORM_BUFFER:
-                entry.buffer = WebGPUDescriptorSet::sDummyUniformBuffer;
-                break;
-            case WebGPUDescriptorSetLayout::BindGroupEntryType::TEXTURE_VIEW:
-                entry.textureView = WebGPUDescriptorSet::sDummyTextureView;
-                break;
-            case WebGPUDescriptorSetLayout::BindGroupEntryType::SAMPLER:
-                entry.sampler = WebGPUDescriptorSet::sDummySampler;
-                break;
-        }
-    }
-    std::sort(entries.begin(), entries.end(),
-            [](wgpu::BindGroupEntry const& a, wgpu::BindGroupEntry const& b) {
-                return a.binding < b.binding;
-            });
-    return entries;
-}
-
 WebGPUDescriptorSet::WebGPUDescriptorSet(wgpu::BindGroupLayout const& layout,
         std::vector<WebGPUDescriptorSetLayout::BindGroupEntryInfo> const& bindGroupEntries)
     : mLayout(layout),
-      mEntriesSortedByBinding(createDummyEntriesSortedByBinding(bindGroupEntries)) {
+      mEntriesWithDynamicOffsetsCount(std::count_if(bindGroupEntries.begin(),
+              bindGroupEntries.end(), [](auto const& entry) { return entry.hasDynamicOffset; })) {
+
+    mEntries.resize(bindGroupEntries.size());
+    for (size_t i = 0; i < bindGroupEntries.size(); ++i) {
+        mEntries[i].binding = bindGroupEntries[i].binding;
+    }
     // Establish the size of entries based on the layout. This should be reliable and efficient.
     assert_invariant(INVALID_INDEX > mEntryIndexByBinding.size());
     for (size_t i = 0; i < mEntryIndexByBinding.size(); i++) {
         mEntryIndexByBinding[i] = INVALID_INDEX;
     }
-    for (size_t index = 0; index < mEntriesSortedByBinding.size(); index++) {
+    for (size_t index = 0; index < mEntries.size(); index++) {
-        wgpu::BindGroupEntry const& entry = mEntriesSortedByBinding[index];
+        wgpu::BindGroupEntry const& entry = mEntries[index];
         assert_invariant(entry.binding < mEntryIndexByBinding.size());
         mEntryIndexByBinding[entry.binding] = static_cast<uint8_t>(index);
     }
-    for (auto const& entry : bindGroupEntries) {
-        if (entry.hasDynamicOffset) {
-            assert_invariant(entry.binding < mEntriesByBindingWithDynamicOffsets.size());
-            mEntriesByBindingWithDynamicOffsets[entry.binding] = true;
-        }
-    }
-    mDynamicOffsets.reserve(mEntriesSortedByBinding.size());
 }
 
 WebGPUDescriptorSet::~WebGPUDescriptorSet() {
@@ -391,15 +452,15 @@ wgpu::BindGroup WebGPUDescriptorSet::lockAndReturn(const wgpu::Device& device) {
     // TODO label? Should we just copy layout label?
     wgpu::BindGroupDescriptor desc{
         .layout = mLayout,
-        .entryCount = mEntriesSortedByBinding.size(),
+        .entryCount = mEntries.size(),
-        .entries = mEntriesSortedByBinding.data()
+        .entries = mEntries.data()
     };
     mBindGroup = device.CreateBindGroup(&desc);
     FILAMENT_CHECK_POSTCONDITION(mBindGroup) << "Failed to create bind group?";
     // once we have created the bind group itself we should no longer need any other state
     mLayout = nullptr;
-    mEntriesSortedByBinding.clear();
+    mEntries.clear();
-    mEntriesSortedByBinding.shrink_to_fit();
+    mEntries.shrink_to_fit();
     return mBindGroup;
 }
 
@@ -417,85 +478,86 @@ void WebGPUDescriptorSet::addEntry(unsigned int index, wgpu::BindGroupEntry&& en
             << index;
     uint8_t entryIndex = mEntryIndexByBinding[index];
     FILAMENT_CHECK_POSTCONDITION(
-            entryIndex != INVALID_INDEX && entryIndex < mEntriesSortedByBinding.size())
+            entryIndex != INVALID_INDEX && entryIndex < mEntries.size())
             << "Invalid binding " << index;
     entry.binding = index;
-    mEntriesSortedByBinding[entryIndex] = std::move(entry);
+    mEntries[entryIndex] = std::move(entry);
-    mEntriesByBindingAdded[index] = true;
-}
-
-uint32_t const* WebGPUDescriptorSet::setDynamicOffsets(uint32_t const* offsets) {
-    // mDynamicOffsets already reserves enough memory for the number of entries in the set
-    mDynamicOffsets.clear();
-    // this implementation copies the offsets to mDynamicOffsets, but also adds values for
-    // unused entries TODO: is this necessary?
-    size_t inputIndex = 0;
-    size_t outputIndex = 0;
-    for (auto const& entry : mEntriesSortedByBinding) {
-        if (mEntriesByBindingWithDynamicOffsets[entry.binding]) {
-            if (mEntriesByBindingAdded[entry.binding]) {
-                mDynamicOffsets[outputIndex++] = offsets[inputIndex++];
-            } else {
-                mDynamicOffsets[outputIndex++] = 0; // dummy offset, as it was never added
-            }
-        }
-    }
-    return mDynamicOffsets.data();
 }
 
 size_t WebGPUDescriptorSet::countEntitiesWithDynamicOffsets() const {
-    return mEntriesByBindingWithDynamicOffsets.count();
+    return mEntriesWithDynamicOffsetsCount;
 }
 
-// From createTextureR
 WGPUTexture::WGPUTexture(SamplerType target, uint8_t levels, TextureFormat format, uint8_t samples,
         uint32_t width, uint32_t height, uint32_t depth, TextureUsage usage,
-        wgpu::Device device) noexcept {
+        wgpu::Device const& device) noexcept {
-
+    assert_invariant(
-    // First the texture aspect
+            samples == 1 ||
-    wgpu::TextureDescriptor desc;
+            samples == 4 &&
-
+                    "An invalid number of samples were requested, as WGPU requires the sample "
+                    "count to either be 1 (no multisampling) or 4, at least as of April 2025 of "
+                    "the spec. See https://www.w3.org/TR/webgpu/#texture-creation or "
+                    "https://gpuweb.github.io/gpuweb/#multisample-state");
+    // First, the texture aspect, starting with the defaults/basic configuration
+    mUsage = fToWGPUTextureUsage(usage);
+    mFormat = fToWGPUTextureFormat(format);
+    mAspect = fToWGPUTextureViewAspect(usage, format);
+    mBlockWidth = filament::backend::getBlockWidth(format);
+    mBlockHeight = filament::backend::getBlockHeight(format);
+    wgpu::TextureDescriptor textureDescriptor{
+        .label = getUserTextureLabel(target),
+        .usage = mUsage,
+        .dimension = target == SamplerType::SAMPLER_3D ? wgpu::TextureDimension::e3D
+                                                       : wgpu::TextureDimension::e2D,
+        .size = { .width = width, .height = height, .depthOrArrayLayers = depth },
+        .format = mFormat,
+        .mipLevelCount = levels,
+        .sampleCount = samples,
+        // TODO Is this fine? Could do all-the-things, a naive mapping or get something from
+        // Filament
+        .viewFormatCount = 0,
+        .viewFormats = nullptr,
+    };
+    // adjust for specific cases
     switch (target) {
-        case SamplerType::SAMPLER_CUBEMAP:
-        case SamplerType::SAMPLER_CUBEMAP_ARRAY:
         case SamplerType::SAMPLER_2D:
+            mArrayLayerCount = 1;
+            break;
         case SamplerType::SAMPLER_2D_ARRAY:
-        // Should be safe to assume external is 2d
+            mArrayLayerCount = textureDescriptor.size.depthOrArrayLayers;
-        case SamplerType::SAMPLER_EXTERNAL: {
-            desc.dimension = wgpu::TextureDimension::e2D;
             break;
-        }
+        case SamplerType::SAMPLER_CUBEMAP:
-        case SamplerType::SAMPLER_3D: {
+            textureDescriptor.size.depthOrArrayLayers = 6;
-            desc.dimension = wgpu::TextureDimension::e3D;
+            mArrayLayerCount = textureDescriptor.size.depthOrArrayLayers;
+            break;
+        case SamplerType::SAMPLER_EXTERNAL:
+        case SamplerType::SAMPLER_3D:
+            mArrayLayerCount = 1;
+            break;
+        case SamplerType::SAMPLER_CUBEMAP_ARRAY:
+            textureDescriptor.size.depthOrArrayLayers = depth * 6;
+            mArrayLayerCount = textureDescriptor.size.depthOrArrayLayers;
             break;
-        }
     }
-    desc.size = { .width = width, .height = height, .depthOrArrayLayers = depth };
+    assert_invariant(textureDescriptor.format != wgpu::TextureFormat::Undefined &&
-    desc.format = fToWGPUTextureFormat(format);
+                     "Could not find appropriate WebGPU format");
-    assert_invariant(desc.format != wgpu::TextureFormat::Undefined);
+    mTexture = device.CreateTexture(&textureDescriptor);
-
+    FILAMENT_CHECK_POSTCONDITION(mTexture)
-    // WGPU requires this to be true. Filament should comply
+            << "Failed to create texture for " << textureDescriptor.label;
-    assert(samples == 1 || samples || 4);
+    // Second, the texture view aspect
-
+    mTexView = makeTextureView(0, levels, target);
-    desc.sampleCount = samples;
-    desc.usage = fToWGPUTextureUsage(usage);
-    desc.mipLevelCount = levels;
-
-    // TODO Is this fine? Could do all-the-things, a naive mapping or get something from Filament
-    desc.viewFormats = nullptr;
-
-    texture = device.CreateTexture(&desc);
-
-    // TODO should a default levelCount be something other than 0? Sample count?
-    texView = makeTextureView(0, 1);
 }
-// From createTextureViewR
+
 WGPUTexture::WGPUTexture(WGPUTexture* src, uint8_t baseLevel, uint8_t levelCount) noexcept {
-    texture = src->texture;
+    mTexture = src->mTexture;
-    texView = makeTextureView(baseLevel, levelCount);
+    mAspect = src->mAspect;
+    mBlockWidth = src->mBlockWidth;
+    mBlockHeight = src->mBlockHeight;
+
+    mTexView = makeTextureView(baseLevel, levelCount, target);
 }
 
-wgpu::TextureUsage WGPUTexture::fToWGPUTextureUsage(const TextureUsage& fUsage) {
+wgpu::TextureUsage WGPUTexture::fToWGPUTextureUsage(TextureUsage const& fUsage) {
     wgpu::TextureUsage retUsage = wgpu::TextureUsage::None;
 
     // Basing this mapping off of VulkanTexture.cpp's getUsage func and suggestions from Gemini
@@ -543,8 +605,9 @@ wgpu::TextureUsage WGPUTexture::fToWGPUTextureUsage(const TextureUsage& fUsage)
     //  PROTECTED
     return retUsage;
 }
-wgpu::TextureFormat WGPUTexture::fToWGPUTextureFormat(const TextureFormat& fUsage) {
+
-    switch (fUsage) {
+wgpu::TextureFormat WGPUTexture::fToWGPUTextureFormat(TextureFormat const& fFormat) {
+    switch (fFormat) {
         case filament::backend::TextureFormat::R8:
             return wgpu::TextureFormat::R8Unorm;
         case filament::backend::TextureFormat::R8_SNORM:
@@ -783,80 +846,224 @@ wgpu::TextureFormat WGPUTexture::fToWGPUTextureFormat(const TextureFormat& fUsag
     }
 }
 
-wgpu::TextureView WGPUTexture::makeTextureView(const uint8_t& baseLevel,
+wgpu::TextureAspect WGPUTexture::fToWGPUTextureViewAspect(TextureUsage const& fUsage,
-        const uint8_t& levelCount) {
+        TextureFormat const& fFormat) {
-    wgpu::TextureViewDescriptor desc;
-    desc.baseMipLevel = baseLevel;
-    desc.mipLevelCount = levelCount;
 
-    // baseArrayLayer is required, making a guess
+    const bool isDepth = any(fUsage & TextureUsage::DEPTH_ATTACHMENT);
-    desc.baseArrayLayer = 0;
+    const bool isStencil = any(fUsage & TextureUsage::STENCIL_ATTACHMENT);
-    // Have not found an analouge to aspect in other drivers, but ALL should be unrestrictive.
+    const bool isColor = any(fUsage & TextureUsage::COLOR_ATTACHMENT);
-    // TODO Can we make this better?
+    const bool isSample = (fUsage == TextureUsage::SAMPLEABLE);
-    desc.aspect = wgpu::TextureAspect::All;
-
-    // The rest of the properties should be fine to leave as default, using the texture params.
-    desc.label = "TODO";
-
-    desc.format = wgpu::TextureFormat::Undefined;
-    desc.dimension = wgpu::TextureViewDimension::Undefined;
-    desc.usage = wgpu::TextureUsage::None;
-
-    return texture.CreateView(&desc);
-}
-
-WGPURenderTarget::Attachment WGPURenderTarget::getDrawColorAttachment(size_t index) {
-    assert_invariant( index < MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT);
-    auto result = color[index];
-    if (index == 0 && defaultRenderTarget) {
 
+    if (isDepth && !isColor && !isStencil) {
+        return wgpu::TextureAspect::DepthOnly;
     }
 
-    return result;
+    if (isStencil && !isColor && !isDepth) {
+        return wgpu::TextureAspect::StencilOnly;
+    }
+
+    if (fFormat == filament::backend::TextureFormat::DEPTH32F ||
+            fFormat == filament::backend::TextureFormat::DEPTH24 ||
+            fFormat == filament::backend::TextureFormat::DEPTH16) {
+        return wgpu::TextureAspect::DepthOnly;
+    }
+
+    if (fFormat == filament::backend::TextureFormat::STENCIL8) {
+        return wgpu::TextureAspect::StencilOnly;
+    }
+
+    if (fFormat == filament::backend::TextureFormat::DEPTH24_STENCIL8 ||
+            fFormat == filament::backend::TextureFormat::DEPTH32F_STENCIL8) {
+        if (isSample) {
+            return wgpu::TextureAspect::DepthOnly;
+        }
+    }
+
+    return wgpu::TextureAspect::All;
 }
 
+wgpu::TextureView WGPUTexture::makeTextureView(const uint8_t& baseLevel, const uint8_t& levelCount,
+        SamplerType target) {
+
+    wgpu::TextureViewDescriptor textureViewDescriptor{
+        .label = getUserTextureViewLabel(target),
+        .format = mFormat,
+        .baseMipLevel = baseLevel,
+        .mipLevelCount = levelCount,
+        // TODO: check if this baseArrayLayer assumption is correct
+        .baseArrayLayer = 0,
+        .arrayLayerCount = mArrayLayerCount,
+        .aspect = mAspect,
+        .usage = mUsage
+    };
+
+    switch (target) {
+        case SamplerType::SAMPLER_2D:
+            textureViewDescriptor.dimension = wgpu::TextureViewDimension::e2D;
+            break;
+        case SamplerType::SAMPLER_2D_ARRAY:
+            textureViewDescriptor.dimension = wgpu::TextureViewDimension::e2DArray;
+            break;
+        case SamplerType::SAMPLER_CUBEMAP:
+            textureViewDescriptor.dimension = wgpu::TextureViewDimension::Cube;
+            break;
+        case SamplerType::SAMPLER_EXTERNAL:
+            textureViewDescriptor.dimension = wgpu::TextureViewDimension::e2D;
+            break;
+        case SamplerType::SAMPLER_3D:
+            textureViewDescriptor.dimension = wgpu::TextureViewDimension::e3D;
+            break;
+        case SamplerType::SAMPLER_CUBEMAP_ARRAY:
+            textureViewDescriptor.dimension = wgpu::TextureViewDimension::CubeArray;
+            break;
+    }
+    wgpu::TextureView textureView = mTexture.CreateView(&textureViewDescriptor);
+    FILAMENT_CHECK_POSTCONDITION(textureView)
+            << "Failed to create texture view " << textureViewDescriptor.label;
+    return textureView;
+}
+
+WGPURenderTarget::WGPURenderTarget(uint32_t width, uint32_t height, uint8_t samples,
+        const MRT& colorAttachmentsMRT,
+        const Attachment& depthAttachmentInfo,
+        const Attachment& stencilAttachmentInfo)
+    : HwRenderTarget(width, height),
+      defaultRenderTarget(false),
+      samples(samples),
+      mColorAttachments(colorAttachmentsMRT),
+      mDepthAttachment(depthAttachmentInfo),
+      mStencilAttachment(stencilAttachmentInfo) {
+    mColorAttachmentDescriptors.reserve(MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT);
+}
+
+// Static helper to map MRT index to TargetBufferFlags
+TargetBufferFlags WGPURenderTarget::getTargetBufferFlagsAt(int mrtIndex) {
+    if (mrtIndex < 0 || mrtIndex >= MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT) {
+        return TargetBufferFlags::NONE;
+    }
+    // This mapping assumes TargetBufferFlags::COLOR_0, COLOR_1 etc. are contiguous
+    return static_cast<TargetBufferFlags>(
+            static_cast<uint32_t>(TargetBufferFlags::COLOR0) << mrtIndex);
+}
+
+// Corrected getLoadOperation
 wgpu::LoadOp WGPURenderTarget::getLoadOperation(RenderPassParams const& params,
-                                             TargetBufferFlags buffer) {
+                                                TargetBufferFlags bufferToOperateOn) {
-    auto clearFlags = params.flags.clear;
+    if (any(params.flags.clear & bufferToOperateOn)) {
-    auto discardStartFlags = params.flags.discardStart;
-    if (any(clearFlags & buffer)) {
-        return wgpu::LoadOp::Clear;
-    } else if (any(discardStartFlags & buffer)) {
         return wgpu::LoadOp::Clear;
     }
+    if (any(params.flags.discardStart & bufferToOperateOn)) {
+        return wgpu::LoadOp::Clear; // Or wgpu::LoadOp::Undefined if clear is not desired on discard
+    }
     return wgpu::LoadOp::Load;
 }
 
+// Corrected getStoreOperation
 wgpu::StoreOp WGPURenderTarget::getStoreOperation(RenderPassParams const& params,
-                                               TargetBufferFlags buffer) {
+                                                  TargetBufferFlags bufferToOperateOn) {
-    const auto discardEndFlags = params.flags.discardEnd;
+    if (any(params.flags.discardEnd & bufferToOperateOn)) {
-    if (any(discardEndFlags & buffer)) {
         return wgpu::StoreOp::Discard;
     }
     return wgpu::StoreOp::Store;
 }
-void WGPURenderTarget::setUpRenderPassAttachments(wgpu::RenderPassDescriptor& descriptor,
+
-        wgpu::TextureView const& textureView, RenderPassParams const& params) {
+void WGPURenderTarget::setUpRenderPassAttachments(
-    // auto discardFlags = params.flags.discardEnd;
+        wgpu::RenderPassDescriptor& descriptor,
-    // (void) discardFlags;
+        RenderPassParams const& params,
-    // std::vector<wgpu::RenderPassColorAttachment> colorAttachments;
+        wgpu::TextureView const& defaultColorTextureView,
-    colorAttachments.clear();
+        wgpu::TextureView const& defaultDepthStencilTextureView,
-    for (size_t i = 0; i < 1/*MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT*/; i++) {
+        wgpu::TextureView const* customColorTextureViews,
-        // auto attachment = getDrawColorAttachment(i);
+        uint32_t customColorTextureViewCount,
-        // if (attachment) {
+        wgpu::TextureView const& customDepthTextureView,
-            wgpu::RenderPassColorAttachment colorAttachment;
+        wgpu::TextureView const& customStencilTextureView) {
-            colorAttachment.view = textureView;
+    mColorAttachmentDescriptors.clear();
-            colorAttachment.loadOp  = getLoadOperation(params, getTargetBufferFlagsAt(i));
+    mHasDepthStencilAttachment = false;
-            colorAttachment.storeOp = getStoreOperation(params, getTargetBufferFlagsAt(i));
+
-            colorAttachment.clearValue = { params.clearColor.r, params.clearColor.g, params.clearColor.b, params.clearColor.a };
+    if (defaultRenderTarget) {
-            colorAttachments.emplace_back(colorAttachment);
+        assert_invariant(defaultColorTextureView);
-        // }
+        wgpu::RenderPassColorAttachment colorAttDesc{};
+        colorAttDesc.view = defaultColorTextureView;
+        colorAttDesc.resolveTarget = nullptr;
+        colorAttDesc.loadOp = WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::COLOR0);
+        colorAttDesc.storeOp = WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::COLOR0);
+        colorAttDesc.clearValue = {params.clearColor.r, params.clearColor.g,
+                                   params.clearColor.b, params.clearColor.a};
+        mColorAttachmentDescriptors.push_back(colorAttDesc);
+
+        if (defaultDepthStencilTextureView) {
+            mDepthStencilAttachmentDescriptor = {
+                .view = defaultDepthStencilTextureView,
+                .depthLoadOp = WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::DEPTH),
+                .depthStoreOp = WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::DEPTH),
+                .depthClearValue = static_cast<float>(params.clearDepth),
+                .depthReadOnly = (params.readOnlyDepthStencil & RenderPassParams::READONLY_DEPTH) > 0,
+                .stencilLoadOp = WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::STENCIL),
+                .stencilStoreOp = WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::STENCIL),
+                .stencilClearValue = params.clearStencil,
+                .stencilReadOnly = (params.readOnlyDepthStencil & RenderPassParams::READONLY_STENCIL) > 0,
+            };
+            mHasDepthStencilAttachment = true;
+        }
+    } else { // Custom Render Target
+        for (uint32_t i = 0; i < customColorTextureViewCount; ++i) {
+            if (customColorTextureViews[i]) {
+                wgpu::RenderPassColorAttachment colorAttDesc{};
+                colorAttDesc.view = customColorTextureViews[i];
+                colorAttDesc.resolveTarget = nullptr; // TODO: MSAA resolve for custom RT
+                colorAttDesc.loadOp = WGPURenderTarget::getLoadOperation(params, getTargetBufferFlagsAt(i));
+                colorAttDesc.storeOp = WGPURenderTarget::getStoreOperation(params, getTargetBufferFlagsAt(i));
+                colorAttDesc.clearValue = {params.clearColor.r, params.clearColor.g,
+                                           params.clearColor.b, params.clearColor.a};
+                mColorAttachmentDescriptors.push_back(colorAttDesc);
+            }
+        }
+
+        wgpu::TextureView combinedDsView = customDepthTextureView ? customDepthTextureView : customStencilTextureView;
+
+        if (combinedDsView) {
+            mDepthStencilAttachmentDescriptor = {};
+            mDepthStencilAttachmentDescriptor.view = combinedDsView;
+
+            if (customDepthTextureView) {
+                mDepthStencilAttachmentDescriptor.depthLoadOp = WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::DEPTH);
+                mDepthStencilAttachmentDescriptor.depthStoreOp = WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::DEPTH);
+                mDepthStencilAttachmentDescriptor.depthClearValue = static_cast<float>(params.clearDepth);
+                mDepthStencilAttachmentDescriptor.depthReadOnly = (params.readOnlyDepthStencil & RenderPassParams::READONLY_DEPTH) > 0;
+            } else {
+                mDepthStencilAttachmentDescriptor.depthLoadOp = wgpu::LoadOp::Undefined;
+                mDepthStencilAttachmentDescriptor.depthStoreOp = wgpu::StoreOp::Undefined;
+                mDepthStencilAttachmentDescriptor.depthReadOnly = true;
+            }
+
+            if (customStencilTextureView) {
+                mDepthStencilAttachmentDescriptor.stencilLoadOp = WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::STENCIL);
+                mDepthStencilAttachmentDescriptor.stencilStoreOp = WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::STENCIL);
+                mDepthStencilAttachmentDescriptor.stencilClearValue = params.clearStencil;
+                mDepthStencilAttachmentDescriptor.stencilReadOnly = (params.readOnlyDepthStencil & RenderPassParams::READONLY_STENCIL) > 0;
+            } else {
+                mDepthStencilAttachmentDescriptor.stencilLoadOp = wgpu::LoadOp::Undefined;
+                mDepthStencilAttachmentDescriptor.stencilStoreOp = wgpu::StoreOp::Undefined;
+                mDepthStencilAttachmentDescriptor.stencilReadOnly = true;
+            }
+            mHasDepthStencilAttachment = true;
+        }
     }
-    descriptor.colorAttachments = colorAttachments.data();
+
-    descriptor.colorAttachmentCount = colorAttachments.size();
+    descriptor.colorAttachmentCount = mColorAttachmentDescriptors.size();
-    descriptor.depthStencilAttachment = nullptr;
+    descriptor.colorAttachments = mColorAttachmentDescriptors.data();
-    descriptor.timestampWrites = nullptr;
+    descriptor.depthStencilAttachment = mHasDepthStencilAttachment ? &mDepthStencilAttachmentDescriptor : nullptr;
+    // descriptor.sampleCount was removed from the core spec. If your webgpu.h still has it,
+    // and your Dawn version expects it, you might need to set it here based on this->samples.
+    // e.g., descriptor.sampleCount = this->samples;
 }
 
+math::uint2 WGPURenderTarget::getAttachmentSize() const noexcept {
+    if (!defaultRenderTarget) {
+        return {width, height};
+    }
+    // For default RT, size is dynamic and usually obtained from the swapchain.
+    // The caller (WebGPUDriver::beginRenderPass) should know the current swapchain size.
+    return {0,0};
+}
 
 }// namespace filament::backend

filament/backend/src/webgpu/WebGPUHandles.h

@@ -28,7 +28,6 @@
 #include <webgpu/webgpu_cpp.h>
 
 #include <array>
-#include <bitset>
 #include <cstdint>
 #include <vector>
 
@@ -44,7 +43,6 @@ public:
     std::vector<wgpu::ConstantEntry> constants;
 };
 
-struct WGPUBufferObject;
 
 // VertexBufferInfo contains layout info for Vertex Buffer based on WebGPU structs. In WebGPU each
 // VertexBufferLayout is associated with a single vertex buffer. So number of mVertexBufferLayout
@@ -74,8 +72,8 @@ public:
 
 private:
     // TODO: can we do better in terms on heap management.
-    std::vector<wgpu::VertexBufferLayout> mVertexBufferLayout {};
+    std::vector<wgpu::VertexBufferLayout> mVertexBufferLayout{};
-    std::vector<std::vector<wgpu::VertexAttribute>> mAttributes {};
+    std::vector<std::vector<wgpu::VertexAttribute>> mAttributes{};
 };
 
 struct WGPUVertexBuffer : public HwVertexBuffer {
@@ -86,33 +84,37 @@ struct WGPUVertexBuffer : public HwVertexBuffer {
     utils::FixedCapacityVector<wgpu::Buffer> buffers;
 };
 
-struct WGPUIndexBuffer : public HwIndexBuffer {
+class WGPUBufferBase {
+public:
+    void createBuffer(wgpu::Device const& device, wgpu::BufferUsage usage, uint32_t size,
+            char const* label);
+    void updateGPUBuffer(BufferDescriptor& bufferDescriptor, uint32_t byteOffset,
+            wgpu::Queue queue);
+    const wgpu::Buffer& getBuffer() const { return buffer; }
+protected:
+    wgpu::Buffer buffer;
+private:
+    // 4 bytes to hold any extra chunk we need.
+    std::array<uint8_t,4> mRemainderChunk;
+};
+
+class WGPUIndexBuffer : public HwIndexBuffer, public WGPUBufferBase {
+public:
     WGPUIndexBuffer(wgpu::Device const &device, uint8_t elementSize,
                     uint32_t indexCount);
-
-    wgpu::Buffer buffer;
     wgpu::IndexFormat indexFormat;
 };
 
-struct WGPUBufferObject : HwBufferObject {
+class WGPUBufferObject : public HwBufferObject, public WGPUBufferBase {
+public:
     WGPUBufferObject(wgpu::Device const &device, BufferObjectBinding bindingType, uint32_t byteCount);
-
-    wgpu::Buffer buffer = nullptr;
-    const BufferObjectBinding bufferObjectBinding;
 };
 
 class WebGPUDescriptorSetLayout final : public HwDescriptorSetLayout {
 public:
 
-    enum class BindGroupEntryType : uint8_t {
-        UNIFORM_BUFFER,
-        TEXTURE_VIEW,
-        SAMPLER
-    };
-
     struct BindGroupEntryInfo final {
         uint8_t binding = 0;
-        BindGroupEntryType type = BindGroupEntryType::UNIFORM_BUFFER;
         bool hasDynamicOffset = false;
     };
 
@@ -125,7 +127,7 @@ public:
 
 private:
     // TODO: If this is useful elsewhere, remove it from this class
-    // Convert Filament Shader Stage Flags bitmask to webgpu equivilant
+    // Convert Filament Shader Stage Flags bitmask to webgpu equivalent
     static wgpu::ShaderStage filamentStageToWGPUStage(ShaderStageFlags fFlags);
     std::vector<BindGroupEntryInfo> mBindGroupEntries;
     wgpu::BindGroupLayout mLayout;
@@ -133,8 +135,6 @@ private:
 
 class WebGPUDescriptorSet final : public HwDescriptorSet {
 public:
-    static void initializeDummyResourcesIfNotAlready(wgpu::Device const&,
-            wgpu::TextureFormat aColorFormat);
 
     WebGPUDescriptorSet(wgpu::BindGroupLayout const& layout,
             std::vector<WebGPUDescriptorSetLayout::BindGroupEntryInfo> const& bindGroupEntries);
@@ -142,30 +142,15 @@ public:
 
     wgpu::BindGroup lockAndReturn(wgpu::Device const&);
     void addEntry(unsigned int index, wgpu::BindGroupEntry&& entry);
-    [[nodiscard]] uint32_t const* setDynamicOffsets(uint32_t const* offsets);
     [[nodiscard]] bool getIsLocked() const { return mBindGroup != nullptr; }
     [[nodiscard]] size_t countEntitiesWithDynamicOffsets() const;
+
 private:
-
-    static wgpu::Buffer sDummyUniformBuffer;
-    static wgpu::Texture sDummyTexture;
-    static wgpu::TextureView sDummyTextureView;
-    static wgpu::Sampler sDummySampler;
-
-    static std::vector<wgpu::BindGroupEntry> createDummyEntriesSortedByBinding(
-            std::vector<filament::backend::WebGPUDescriptorSetLayout::BindGroupEntryInfo> const&);
-
-    // TODO: Consider storing what we used to make the layout. However we need to essentially
-    // Recreate some of the info (Sampler in slot X with the actual sampler) so letting Dawn confirm
-    // there isn't a mismatch may be easiest.
-    // Also storing the wgpu ObjectBase takes care of ownership challenges in theory
     wgpu::BindGroupLayout mLayout = nullptr;
     static constexpr uint8_t INVALID_INDEX = MAX_DESCRIPTOR_COUNT + 1;
-    std::array<uint8_t, MAX_DESCRIPTOR_COUNT> mEntryIndexByBinding {};
+    std::array<uint8_t, MAX_DESCRIPTOR_COUNT> mEntryIndexByBinding{};
-    std::vector<wgpu::BindGroupEntry> mEntriesSortedByBinding;
+    std::vector<wgpu::BindGroupEntry> mEntries;
-    std::bitset<MAX_DESCRIPTOR_COUNT> mEntriesByBindingWithDynamicOffsets {};
+    const size_t mEntriesWithDynamicOffsetsCount;
-    std::bitset<MAX_DESCRIPTOR_COUNT> mEntriesByBindingAdded {};
-    std::vector<uint32_t> mDynamicOffsets;
     wgpu::BindGroup mBindGroup = nullptr;
 };
 
@@ -173,24 +158,37 @@ class WGPUTexture : public HwTexture {
 public:
     WGPUTexture(SamplerType target, uint8_t levels, TextureFormat format, uint8_t samples,
             uint32_t width, uint32_t height, uint32_t depth, TextureUsage usage,
-            wgpu::Device device) noexcept;
+            wgpu::Device const& device) noexcept;
 
     WGPUTexture(WGPUTexture* src, uint8_t baseLevel, uint8_t levelCount) noexcept;
+    wgpu::TextureAspect getAspect() const { return mAspect; }
+    size_t getBlockWidth() const { return mBlockWidth; }
+    size_t getBlockHeight() const { return mBlockHeight; }
 
-    const wgpu::Texture& getTexture() const { return texture; }
+    [[nodiscard]] const wgpu::Texture& getTexture() const { return mTexture; }
-    const wgpu::TextureView& getTexView() const { return texView; }
+    [[nodiscard]] const wgpu::TextureView& getTexView() const { return mTexView; }
 
-    // Public to allow checking for support of a texture format
+    static wgpu::TextureFormat fToWGPUTextureFormat(
-    static wgpu::TextureFormat fToWGPUTextureFormat(const filament::backend::TextureFormat& fUsage);
+            filament::backend::TextureFormat const& fFormat);
+    static wgpu::TextureAspect fToWGPUTextureViewAspect(
+            filament::backend::TextureUsage const& fUsage,
+            filament::backend::TextureFormat const& fFormat);
 
 private:
-    wgpu::TextureView makeTextureView(const uint8_t& baseLevel, const uint8_t& levelCount);
+    wgpu::TextureView makeTextureView(const uint8_t& baseLevel, const uint8_t& levelCount,
+            SamplerType target);
     // CreateTextureR has info for a texture and sampler. Texture Views are needed for binding,
     // along with a sampler Current plan: Inherit the sampler and Texture to always exist (It is a
     // ref counted pointer) when making views. View is optional
-    wgpu::Texture texture = nullptr;
+    wgpu::Texture mTexture = nullptr;
-    wgpu::TextureView texView = nullptr;
+    wgpu::TextureUsage mUsage = wgpu::TextureUsage::None;
-    wgpu::TextureUsage fToWGPUTextureUsage(const filament::backend::TextureUsage& fUsage);
+    wgpu::TextureFormat mFormat = wgpu::TextureFormat::Undefined;
+    wgpu::TextureAspect mAspect = wgpu::TextureAspect::Undefined;
+    uint32_t mArrayLayerCount = 1;
+    wgpu::TextureView mTexView = nullptr;
+    wgpu::TextureUsage fToWGPUTextureUsage(filament::backend::TextureUsage const& fUsage);
+    size_t mBlockWidth;
+    size_t mBlockHeight;
 };
 
 struct WGPURenderPrimitive : public HwRenderPrimitive {
@@ -199,57 +197,66 @@ struct WGPURenderPrimitive : public HwRenderPrimitive {
     WGPUIndexBuffer* indexBuffer = nullptr;
 };
 
+
+
 class WGPURenderTarget : public HwRenderTarget {
 public:
-    class Attachment {
+    using Attachment = TargetBufferInfo; // Using TargetBufferInfo directly for attachments
-    public:
-        friend class WGPURenderTarget;
-
-        Attachment() = default;
-        Attachment(WGPUTexture* gpuTexture, uint8_t level = 0, uint16_t layer = 0)
-            : level(level),
-              layer(layer),
-              texture(gpuTexture->getTexture()),
-              mWGPUTexture(gpuTexture) {}
-        operator bool() const {
-            return mWGPUTexture != nullptr;
-        }
-
-        uint8_t level = 0;
-        uint16_t layer = 0;
-
-    private:
-        wgpu::Texture texture = nullptr;
-        WGPUTexture* mWGPUTexture = nullptr;
-    };
 
     WGPURenderTarget(uint32_t width, uint32_t height, uint8_t samples,
-            Attachment colorAttachments[MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT]);
+            const MRT& colorAttachments,
+            const Attachment& depthAttachment,
+            const Attachment& stencilAttachment);
+
+    // Default constructor for the default render target
     WGPURenderTarget()
         : HwRenderTarget(0, 0),
-          defaultRenderTarget(true) {}
+          defaultRenderTarget(true),
+          samples(1) {}
 
-    void setUpRenderPassAttachments(wgpu::RenderPassDescriptor& descriptor,
+    // Updated signature: takes resolved views for custom RTs, and default views for default RT
-            wgpu::TextureView const& textureView, RenderPassParams const& params);
+    void setUpRenderPassAttachments(
+            wgpu::RenderPassDescriptor& descriptor,
+            RenderPassParams const& params,
+            // For default render target:
+            wgpu::TextureView const& defaultColorTextureView,
+            wgpu::TextureView const& defaultDepthStencilTextureView,
+            // For custom render targets:
+            wgpu::TextureView const* customColorTextureViews, // Array of views
+            uint32_t customColorTextureViewCount,
+            wgpu::TextureView const& customDepthTextureView,
+            wgpu::TextureView const& customStencilTextureView);
 
-    math::uint2 getAttachmentSize() noexcept;
+
+    math::uint2 getAttachmentSize() const noexcept;
 
     bool isDefaultRenderTarget() const { return defaultRenderTarget; }
     uint8_t getSamples() const { return samples; }
 
-    Attachment getDrawColorAttachment(size_t index);
+    // Accessors for the driver to get stored attachment info
-    Attachment getReadColorAttachment(size_t index);
+    const MRT& getColorAttachmentInfos() const { return mColorAttachments; }
+    const Attachment& getDepthAttachmentInfo() const { return mDepthAttachment; }
+    const Attachment& getStencilAttachmentInfo() const { return mStencilAttachment; }
 
+    // Static helpers for load/store operations
     static wgpu::LoadOp getLoadOperation(const RenderPassParams& params, TargetBufferFlags buffer);
     static wgpu::StoreOp getStoreOperation(const RenderPassParams& params, TargetBufferFlags buffer);
+
 private:
+    // Helper to map MRT index to TargetBufferFlags
+    static TargetBufferFlags getTargetBufferFlagsAt(int mrtIndex);
+
     bool defaultRenderTarget = false;
     uint8_t samples = 1;
 
-    Attachment color[MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT] = {};
+    MRT mColorAttachments{};
-    math::uint2 attachmentSize = {};
+    Attachment mDepthAttachment{};
-    std::vector<wgpu::RenderPassColorAttachment> colorAttachments {};
+    Attachment mStencilAttachment{};
-};
 
+    // Cached descriptors for the render pass
+    std::vector<wgpu::RenderPassColorAttachment> mColorAttachmentDescriptors;
+    wgpu::RenderPassDepthStencilAttachment mDepthStencilAttachmentDescriptor{};
+    bool mHasDepthStencilAttachment = false;
+};
 }// namespace filament::backend
 #endif// TNT_FILAMENT_BACKEND_WEBGPUHANDLES_H

filament/backend/test/BackendTest.cpp

@@ -32,6 +32,7 @@ static constexpr size_t CONFIG_COMMAND_BUFFERS_SIZE     = 3 * CONFIG_MIN_COMMAND
 
 using namespace filament;
 using namespace filament::backend;
+using namespace filament::math;
 
 #ifndef FILAMENT_IOS
 #include <imageio/ImageEncoder.h>
@@ -45,6 +46,7 @@ namespace test {
 Backend BackendTest::sBackend = Backend::NOOP;
 OperatingSystem BackendTest::sOperatingSystem = OperatingSystem::OTHER;
 bool BackendTest::sIsMobilePlatform = false;
+std::vector<std::string> BackendTest::sFailedImages;
 
 void BackendTest::init(Backend backend, OperatingSystem operatingSystem, bool isMobilePlatform) {
     sBackend = backend;
@@ -63,11 +65,12 @@ BackendTest::~BackendTest() {
     flushAndWait();
     mImageExpectations->evaluate();
     // Note: Don't terminate the driver for OpenGL, as it wipes away the context and removes the buffer from the screen.
-    if (sBackend == Backend::OPENGL) {
+    if (sBackend != Backend::OPENGL) {
-        return;
+        driver->terminate();
+        delete driver;
     }
-    driver->terminate();
+
-    delete driver;
+    recordFailedImages();
 }
 
 void BackendTest::initializeDriver() {
@@ -104,16 +107,35 @@ Handle<HwSwapChain> BackendTest::createSwapChain() {
     return getDriverApi().createSwapChain(view.ptr, 0);
 }
 
-void BackendTest::fullViewport(RenderPassParams& params) {
+PipelineState BackendTest::getColorWritePipelineState() {
-    fullViewport(params.viewport);
+    PipelineState result;
+    result.rasterState.colorWrite = true;
+    result.rasterState.depthWrite = false;
+    result.rasterState.depthFunc = RasterState::DepthFunc::A;
+    return result;
 }
 
-void BackendTest::fullViewport(Viewport& viewport) {
+filament::backend::Viewport BackendTest::getFullViewport() const {
-    const NativeView& view = getNativeView();
+   const NativeView& view = getNativeView();
-    viewport.left = 0;
+   return Viewport {
-    viewport.bottom = 0;
+       .left = 0,
-    viewport.width = view.width;
+       .bottom = 0,
-    viewport.height = view.height;
+       .width = static_cast<uint32_t>(view.width),
+       .height = static_cast<uint32_t>(view.height)
+   };
+}
+
+filament::backend::RenderPassParams BackendTest::getClearColorRenderPass(float4 color) {
+    RenderPassParams params = {};
+    params.flags.clear = TargetBufferFlags::COLOR;
+    params.flags.discardStart = TargetBufferFlags::ALL;
+    params.flags.discardEnd = TargetBufferFlags::NONE;
+    params.clearColor = color;
+    return params;
+}
+
+filament::backend::RenderPassParams BackendTest::getNoClearRenderPass() {
+    return RenderPassParams{};
 }
 
 void BackendTest::renderTriangle(
@@ -121,14 +143,9 @@ void BackendTest::renderTriangle(
         Handle<filament::backend::HwRenderTarget> renderTarget,
         Handle<filament::backend::HwSwapChain> swapChain,
         Handle<filament::backend::HwProgram> program) {
-    RenderPassParams params = {};
+    RenderPassParams params = getClearColorRenderPass();
-    fullViewport(params);
-    params.flags.clear = TargetBufferFlags::COLOR;
-    params.clearColor = {0.f, 0.f, 1.f, 1.f};
-    params.flags.discardStart = TargetBufferFlags::ALL;
-    params.flags.discardEnd = TargetBufferFlags::NONE;
-    params.viewport.height = 512;
     params.viewport.width = 512;
+    params.viewport.height = 512;
     renderTriangle(pipelineLayout, renderTarget, swapChain, program, params);
 }
 
@@ -167,8 +184,24 @@ bool BackendTest::matchesEnvironment(OperatingSystem operatingSystem) {
     return sOperatingSystem == operatingSystem;
 }
 
-bool BackendTest::matchesEnvironment(OperatingSystem operatingSystem, Backend backend) {
+void BackendTest::markImageAsFailure(std::string failedImageName) {
-    return matchesEnvironment(operatingSystem) && matchesEnvironment(backend);
+    sFailedImages.emplace_back(std::move(failedImageName));
+}
+
+void BackendTest::recordFailedImages() {
+    if (!sFailedImages.empty()) {
+        std::string failedImages;
+        for (auto& failedTestImageName: sFailedImages) {
+            if (failedImages.empty()) {
+                failedImages = failedTestImageName;
+            } else {
+                failedImages.append(",");
+                failedImages.append(failedTestImageName);
+            }
+        }
+        RecordProperty("FailedImages", failedImages);
+    }
+    sFailedImages.clear();
 }
 
 class Environment : public ::testing::Environment {

filament/backend/test/BackendTest.h

@@ -38,6 +38,9 @@ public:
     static OperatingSystem sOperatingSystem;
     static bool sIsMobilePlatform;
 
+    // Takes the name of the image that wasn't correct, without the .png suffix
+    static void markImageAsFailure(std::string failedImageName);
+
 protected:
 
     BackendTest();
@@ -49,9 +52,14 @@ protected:
 
     filament::backend::Handle<filament::backend::HwSwapChain> createSwapChain();
 
-    // Helper methods to set the viewport to the full extent of the swap chain.
+    static filament::backend::PipelineState getColorWritePipelineState();
-    static void fullViewport(filament::backend::RenderPassParams& params);
+
-    static void fullViewport(filament::backend::Viewport& viewport);
+    // Gets the full back buffer's viewport
+    filament::backend::Viewport getFullViewport() const;
+    // If color is unset this defaults to using opaque cyan
+    static filament::backend::RenderPassParams getClearColorRenderPass(
+            filament::math::float4 color = filament::math::float4(0, 1, 1, 1));
+    static filament::backend::RenderPassParams getNoClearRenderPass();
 
     void renderTriangle(
             filament::backend::PipelineLayout const& pipelineLayout,
@@ -73,8 +81,13 @@ protected:
 
     static bool matchesEnvironment(Backend backend);
     static bool matchesEnvironment(OperatingSystem operatingSystem);
-    static bool matchesEnvironment(OperatingSystem operatingSystem, Backend backend);
 private:
+    // Adds all the images that failed an ImageExpectation to the XML metadata for the current tests
+    // case. Add --gtest_output=xml as a command line argument to generate a test_detail.xml file in
+    // the directory where the tests are run.
+    static void recordFailedImages();
+
+    static std::vector<std::string> sFailedImages;
 
     filament::backend::Driver* driver = nullptr;
     filament::backend::CommandBufferQueue commandBufferQueue;

filament/backend/test/ImageExpectations.cpp

@@ -21,6 +21,7 @@
 #include "utils/Hash.h"
 #include <fstream>
 
+#include "BackendTest.h"
 #include "backend/PixelBufferDescriptor.h"
 #include "private/backend/DriverApi.h"
 
@@ -32,6 +33,8 @@
 
 #endif
 
+namespace test {
+
 ScreenshotParams::ScreenshotParams(int width, int height, std::string fileName,
         uint32_t expectedHash, bool isSrgb)
     : mWidth(width),
@@ -80,6 +83,10 @@ std::string ScreenshotParams::expectedFilePath() const {
     return absl::StrFormat("%s/%s", expectedDirectoryPath(), expectedFileName());
 }
 
+const std::string ScreenshotParams::filePrefix() const {
+    return mFileName;
+}
+
 ImageExpectation::ImageExpectation(const char* fileName, int lineNumber,
         filament::backend::DriverApi& api, ScreenshotParams params,
         filament::backend::RenderTargetHandle renderTarget)
@@ -113,7 +120,11 @@ void ImageExpectation::compareImage() const {
 #ifndef FILAMENT_IOS
         LoadedPng loadedImage(mParams.expectedFilePath());
         uint32_t loadedImageHash = loadedImage.hash();
-        EXPECT_THAT(actualHash, testing::Eq(loadedImageHash)) << mParams.expectedFileName();
+        auto compareToImageMatcher = testing::Eq(loadedImageHash);
+        if (!testing::Matches(compareToImageMatcher)(actualHash)) {
+            BackendTest::markImageAsFailure(mParams.filePrefix());
+        }
+        EXPECT_THAT(actualHash, compareToImageMatcher) << mParams.expectedFileName();
 #endif
         // For builds that can't load PNGs (currently iOS only) use the expected hash.
         EXPECT_THAT(actualHash, testing::Eq(mParams.expectedHash())) << mParams.expectedFileName();
@@ -200,6 +211,10 @@ uint32_t RenderTargetDump::hash() const {
     return mInternal->hash();
 }
 
+const std::vector<unsigned char>& RenderTargetDump::bytes() const {
+    return mInternal->bytes;
+}
+
 bool RenderTargetDump::bytesFilled() const {
     return mInternal->bytesFilled;
 }
@@ -237,3 +252,5 @@ uint32_t LoadedPng::hash() const {
 const std::vector<unsigned char>& LoadedPng::bytes() const {
     return mBytes;
 }
+
+} // namespace test

filament/backend/test/ImageExpectations.h

@@ -35,6 +35,8 @@ do {                                                                \
         screenshotParams);                                          \
 } while (0)
 
+namespace test {
+
 /**
  * Stores user-provided configuration values for an image expectation
  */
@@ -54,6 +56,7 @@ public:
     static std::string expectedDirectoryPath();
     std::string expectedFileName() const;
     std::string expectedFilePath() const;
+    const std::string filePrefix() const;
 
 private:
     int mWidth;
@@ -82,6 +85,12 @@ public:
      * @return The hash of the stored bytes.
      */
     uint32_t hash() const;
+    /**
+     * Gets the bytes of the render target. The hash should usually be preferable for comparisons
+     * but this is available for debugging.
+     * @return The stored bytes.
+     */
+    const std::vector<unsigned char>& bytes() const;
     /**
      * Thread safe as this is backed by an atomic.
      * Once this returns true it will never return false.
@@ -153,4 +162,6 @@ private:
     std::vector<std::unique_ptr<ImageExpectation>> mExpectations;
 };
 
+} // namespace test
+
 #endif //TNT_IMAGE_EXPECTATIONS_H

filament/backend/test/Shader.cpp

@@ -56,26 +56,35 @@ Shader::Shader(DriverApi& api, Cleanup& cleanup, ShaderConfig config) : mCleanup
     mProgram = cleanup.add(api.createProgram(std::move(prog)));
 
     if (!kLayouts.empty()) {
-        mDescriptorSetLayout =
+        mDescriptorSetLayout = cleanup.add(
-                cleanup.add(api.createDescriptorSetLayout(DescriptorSetLayout{ kLayouts }));
+                api.createDescriptorSetLayout(DescriptorSetLayout{ .bindings = kLayouts }));
     }
 }
 
-filament::backend::DescriptorSetHandle Shader::createDescriptorSet(DriverApi& api) const {
+DescriptorSetHandle Shader::createDescriptorSet(DriverApi& api) const {
     return mCleanup.add(api.createDescriptorSet(mDescriptorSetLayout));
 }
 
-filament::backend::ProgramHandle Shader::getProgram() const {
+ProgramHandle Shader::getProgram() const {
     assert(mProgram);
     EXPECT_THAT(mProgram, ::testing::IsTrue())
                         << "Shader program accessed despite being null.";
     return mProgram;
 }
 
-filament::backend::DescriptorSetLayoutHandle Shader::getDescriptorSetLayout() const {
+DescriptorSetLayoutHandle Shader::getDescriptorSetLayout() const {
     EXPECT_THAT(mDescriptorSetLayout, ::testing::IsTrue())
             << "Shader descriptor set layout accessed despite being null.";
     return mDescriptorSetLayout;
 }
 
+void Shader::addProgramToPipelineState(PipelineState& state) const {
+    state.program = getProgram();
+    // In case another shader was set first, clear the set layout and then set this shader's values.
+    state.pipelineLayout.setLayout = PipelineLayout::SetLayout();
+    if (mDescriptorSetLayout) {
+        state.pipelineLayout.setLayout[0] = { getDescriptorSetLayout() };
+    }
+}
+
 } // namespace test

filament/backend/test/Shader.h

@@ -90,6 +90,8 @@ public:
     filament::backend::ProgramHandle getProgram() const;
     filament::backend::DescriptorSetLayoutHandle getDescriptorSetLayout() const;
 
+    void addProgramToPipelineState(filament::backend::PipelineState& state) const;
+
     filament::backend::DescriptorSetHandle createDescriptorSet(
             filament::backend::DriverApi& api) const;
 

filament/backend/test/ShaderGenerator.cpp

@@ -17,7 +17,6 @@
 #include "ShaderGenerator.h"
 
 #include <GlslangToSpv.h>
-#include <SPVRemapper.h>
 
 #include <spirv_glsl.hpp>
 #include <spirv_msl.hpp>
@@ -119,7 +118,7 @@ ShaderGenerator::Blob ShaderGenerator::transpileShader(ShaderStage stage, std::s
     } else if (backend == Backend::VULKAN) {
         shader.insert(pos, "#define TARGET_VULKAN_ENVIRONMENT\n");
     } else if (backend == Backend::WEBGPU) {
-        shader.insert(pos, "#define TARGET_VULKAN_ENVIRONMENT\n");
+        shader.insert(pos, "#define TARGET_WEBGPU_ENVIRONMENT\n");
     }
 
     const char* shaderCString = shader.c_str();
@@ -187,4 +186,16 @@ Program ShaderGenerator::getProgram(filament::backend::DriverApi&) noexcept {
     return program;
 }
 
+Program ShaderGenerator::getProgramWithPushConstants(filament::backend::DriverApi&,
+        std::array<PushConstants, filament::backend::Program::SHADER_TYPE_COUNT> constants) {
+    Program program;
+    program.shaderLanguage(mShaderLanguage);
+    program.shader(ShaderStage::VERTEX, mVertexBlob.data(), mVertexBlob.size());
+    program.shader(ShaderStage::FRAGMENT, mFragmentBlob.data(), mFragmentBlob.size());
+    for (auto const stage : {ShaderStage::VERTEX, ShaderStage::FRAGMENT }) {
+        program.pushConstants(stage, constants[uint8_t(stage)]);
+    }
+    return program;
+}
+
 } // namespace test

filament/backend/test/ShaderGenerator.h

@@ -48,6 +48,10 @@ public:
 
     filament::backend::Program getProgram(filament::backend::DriverApi&) noexcept;
 
+    using PushConstants = utils::FixedCapacityVector<filament::backend::Program::PushConstant>;
+    filament::backend::Program getProgramWithPushConstants(filament::backend::DriverApi&,
+            std::array<PushConstants, filament::backend::Program::SHADER_TYPE_COUNT> constants);
+
 private:
     using ShaderStage = filament::backend::ShaderStage;
 

filament/backend/test/SharedShaders.cpp

@@ -184,7 +184,7 @@ std::vector<UniformConfig> GetUniformConfig(ShaderUniformType type) {
                     "backend_test", "test_tex", 0,
                     SamplerType::SAMPLER_2D, SamplerFormat::FLOAT, Precision::HIGH, false };
             return {{
-                            "test_tex", DescriptorType::SAMPLER, samplerInfo
+                            "test_tex", DescriptorType::SAMPLER_2D_FLOAT, samplerInfo
                     }};
         }
         default:

filament/backend/test/Skip.h

@@ -32,13 +32,24 @@ do {
     }                                                                                          \
 } while (false)
 
+#define NONFATAL_FAIL_IF(skipEnvironment, rationale)                                           \
+do {                                                                                           \
+    SkipEnvironment skip(skipEnvironment);                                                     \
+    if (skip.matches()) {                                                                      \
+        ADD_FAILURE()                                                                          \
+                << "Failing test as the " << skip.describe() << "\n"                           \
+                << " This test has a known failure where "   \
+                << rationale;                                                                  \
+    }                                                                                          \
+} while (false)
+
 #define FAIL_IF(skipEnvironment, rationale)                                                    \
 do {                                                                                           \
     SkipEnvironment skip(skipEnvironment);                                                     \
     if (skip.matches()) {                                                                      \
         GTEST_FAIL()                                                                           \
                 << "Failing test as the " << skip.describe() << "\n"                           \
-                << " This test should be able to succeed but it needs to fail early because"   \
+                << " This test should be able to succeed but it needs to fail early because "  \
                 << rationale;                                                                  \
     }                                                                                          \
 } while (false)

filament/backend/test/TrianglePrimitive.h

@@ -55,6 +55,8 @@ public:
     void updateIndices(const index_type* indices) noexcept;
     void updateIndices(const index_type* indices, int count, int offset) noexcept;
 
+    VertexInfoHandle getVertexBufferInfo() const { return mVertexBufferInfo; }
+
 private:
 
     size_t mVertexCount = 3;